Daily Papers

As large language models (LLMs) are increasingly integrated into numerous applications across various domains, LLMs' safety becomes a critical concern for both application developers and intended users. Currently, great efforts have been made to develop safety benchmarks with fine-grained taxonomies. However, these benchmarks' taxonomies are disparate with different safety policies. Thus, existing safeguards trained on these benchmarks are either coarse-grained to only distinguish between safe and unsafe, or constrained by the narrow risk taxonomies of a single benchmark. To leverage these fine-grained safety taxonomies across multiple safety benchmarks, in this paper, we propose GSPR, a Generalizable Safety Policy Reasoner to identify unsafe input prompts and LLMs' outputs with violated safety taxonomies through Group Relative Policy Optimization (GRPO). Unlike prior safeguards which only cover a fixed set of risk factors, our GSPR incentivizes its reasoning capability with varied safety taxonomies through our careful cold-start strategy and reward design. Consequently, our GSPR can be trained across multiple safety benchmarks with distinct taxonomies and naturally exhibits powerful generalization ability. We conduct extensive experiments to show that our GSPR significantly improves existing safety guardrails' reasoning capabilities for both safety and category prediction tasks. Moreover, our GSPR not only demonstrates powerful safety generalization abilities but also achieves the least inference token costs with explanations.

As LLMs increasingly impact safety-critical applications, ensuring their safety using guardrails remains a key challenge. This paper proposes GuardReasoner, a new safeguard for LLMs, by guiding the guard model to learn to reason. Concretely, we first create the GuardReasonerTrain dataset, which consists of 127K samples with 460K detailed reasoning steps. Then, we introduce reasoning SFT to unlock the reasoning capability of guard models. In addition, we present hard sample DPO to further strengthen their reasoning ability. In this manner, GuardReasoner achieves better performance, explainability, and generalizability. Extensive experiments and analyses on 13 benchmarks of 3 guardrail tasks demonstrate its superiority. Remarkably, GuardReasoner 8B surpasses GPT-4o+CoT by 5.74% and LLaMA Guard 3 8B by 20.84% F1 score on average. We release the training data, code, and models with different scales (1B, 3B, 8B) of GuardReasoner : https://github.com/yueliu1999/GuardReasoner/.

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation via external guard models-designed to monitor LLM inputs and outputs and block potentially harmful content-has emerged as a prevalent mitigation strategy. Existing approaches of training guard models rely heavily on extensive human curated datasets and struggle with out-of-distribution threats, such as emerging harmful categories or jailbreak attacks. To address these limitations, we propose RSafe, an adaptive reasoning-based safeguard that conducts guided safety reasoning to provide robust protection within the scope of specified safety policies. RSafe operates in two stages: 1) guided reasoning, where it analyzes safety risks of input content through policy-guided step-by-step reasoning, and 2) reinforced alignment, where rule-based RL optimizes its reasoning paths to align with accurate safety prediction. This two-stage training paradigm enables RSafe to internalize safety principles to generalize safety protection capability over unseen or adversarial safety violation scenarios. During inference, RSafe accepts user-specified safety policies to provide enhanced safeguards tailored to specific safety requirements.

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an attacker who keeps adapting or finds another way in. We determine what each reported result implies for that question, allowing results from different safeguard families to be compared under one deployment criterion. The evidence requirements are strongly asymmetric. One attack that obtains harmful help from the deployed service suffices to establish that such help remains, and such attacks appear repeatedly in the coded record. Establishing that little remains cannot follow from the safeguard's own numbers alone; it also requires evidence about what the surrounding system still allows after the safeguard performs its local function. Such evidence is supported or derived in only a small minority of the depth-coded claims, and one such claim bounds its scoped residual. A better local score is therefore not, by itself, a stronger claim about the deployment. Safeguard research cannot stop at raising local scores; a gain has to be judged by whether it makes a deployed system any safer.

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

As large language models (LLMs) become increasingly prevalent, ensuring their robustness against adversarial misuse is crucial. This paper introduces the GAP (Graph of Attacks with Pruning) framework, an advanced approach for generating stealthy jailbreak prompts to evaluate and enhance LLM safeguards. GAP addresses limitations in existing tree-based LLM jailbreak methods by implementing an interconnected graph structure that enables knowledge sharing across attack paths. Our experimental evaluation demonstrates GAP's superiority over existing techniques, achieving a 20.8% increase in attack success rates while reducing query costs by 62.7%. GAP consistently outperforms state-of-the-art methods for attacking both open and closed LLMs, with attack success rates of >96%. Additionally, we present specialized variants like GAP-Auto for automated seed generation and GAP-VLM for multimodal attacks. GAP-generated prompts prove highly effective in improving content moderation systems, increasing true positive detection rates by 108.5% and accuracy by 183.6% when used for fine-tuning. Our implementation is available at https://github.com/dsbuddy/GAP-LLM-Safety.

Red teaming must continually adapt as frontier LLM safeguards evolve, yet existing approaches largely search for adversarial prompts or optimize within fixed attack procedures. We observe that even when an attack becomes ineffective, its underlying mechanisms can remain useful and can be revised or recombined to construct stronger attacks. Based on this insight, we introduce RedDarwin, an agentic framework that shifts the unit of jailbreak evolution from prompts and fixed attacks to executable attack skills. RedDarwin consists of 47 reusable base skills and autonomously revises, composes, executes, and selects them using target-model feedback, allowing successful discoveries to become building blocks for subsequent evolution. RedDarwin produces 65 evolved skills, improving 44 of 47 base attacks and increasing their mean attack success rate (ASR) on AdvBench from 18.8% to 47.3%. These evolved skills consistently outperform baselines on the held-out StrongREJECT and frontier LLMs unseen during evolution; with only 10 target-model queries, RedDarwin achieves 100% ASR on GPT-5.6-Sol, 92% on Claude-Sonnet-5, and 80% on Gemini-3.8-Flash. Analysis of the evolution trajectories further shows that strong attacks often emerge from novel combinations of reusable mechanisms rather than from individually dominant ones. We believe this paradigm can accelerate adaptive red teaming and inform stronger safeguards, creating complementary value for both safety evaluation and defense.

The misuse of large language models (LLMs) has garnered significant attention from the general public and LLM vendors. In response, efforts have been made to align LLMs with human values and intent use. However, a particular type of adversarial prompts, known as jailbreak prompt, has emerged and continuously evolved to bypass the safeguards and elicit harmful content from LLMs. In this paper, we conduct the first measurement study on jailbreak prompts in the wild, with 6,387 prompts collected from four platforms over six months. Leveraging natural language processing technologies and graph-based community detection methods, we discover unique characteristics of jailbreak prompts and their major attack strategies, such as prompt injection and privilege escalation. We also observe that jailbreak prompts increasingly shift from public platforms to private ones, posing new challenges for LLM vendors in proactive detection. To assess the potential harm caused by jailbreak prompts, we create a question set comprising 46,800 samples across 13 forbidden scenarios. Our experiments show that current LLMs and safeguards cannot adequately defend jailbreak prompts in all scenarios. Particularly, we identify two highly effective jailbreak prompts which achieve 0.99 attack success rates on ChatGPT (GPT-3.5) and GPT-4, and they have persisted online for over 100 days. Our work sheds light on the severe and evolving threat landscape of jailbreak prompts. We hope our study can facilitate the research community and LLM vendors in promoting safer and regulated LLMs.

Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are widespread on the web, yet their security posture and exposure to such attacks remain poorly understood. These applications often rely on third-party chatbot plugins that act as intermediaries to commercial LLM APIs, offering non-expert website builders intuitive ways to customize chatbot behaviors. To bridge this gap, we present the first large-scale study of 17 third-party chatbot plugins used by over 10,000 public websites, uncovering previously unknown prompt injection risks in practice. First, 8 of these plugins (used by 8,000 websites) fail to enforce the integrity of the conversation history transmitted in network requests between the website visitor and the chatbot. This oversight amplifies the impact of direct prompt injection attacks by allowing adversaries to forge conversation histories (including fake system messages), boosting their ability to elicit unintended behavior (e.g., code generation) by 3 to 8x. Second, 15 plugins offer tools, such as web-scraping, to enrich the chatbot's context with website-specific content. However, these tools do not distinguish the website's trusted content (e.g., product descriptions) from untrusted, third-party content (e.g., customer reviews), introducing a risk of indirect prompt injection. Notably, we found that ~13% of e-commerce websites have already exposed their chatbots to third-party content. We systematically evaluate both vulnerabilities through controlled experiments grounded in real-world observations, focusing on factors such as system prompt design and the underlying LLM. Our findings show that many plugins adopt insecure practices that undermine the built-in LLM safeguards.

Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational judgment. Unlike prior jailbreaking approaches focused on prompt engineering or algorithmic manipulation, this work highlights the overlooked power of multi-bias interactions in undermining LLM safeguards. We propose CognitiveAttack, a novel red-teaming framework that systematically leverages both individual and combined cognitive biases. By integrating supervised fine-tuning and reinforcement learning, CognitiveAttack generates prompts that embed optimized bias combinations, effectively bypassing safety protocols while maintaining high attack success rates. Experimental results reveal significant vulnerabilities across 30 diverse LLMs, particularly in open-source models. CognitiveAttack achieves a substantially higher attack success rate compared to the SOTA black-box method PAP (60.1% vs. 31.6%), exposing critical limitations in current defense mechanisms. These findings highlight multi-bias interactions as a powerful yet underexplored attack vector. This work introduces a novel interdisciplinary perspective by bridging cognitive science and LLM safety, paving the way for more robust and human-aligned AI systems.

Large language models (LLMs) have shown high agreement with human raters across a variety of tasks, demonstrating potential to ease the challenges of human data collection. In computational social science (CSS), researchers are increasingly leveraging LLM annotations to complement slow and expensive human annotations. Still, guidelines for collecting and using LLM annotations, without compromising the validity of downstream conclusions, remain limited. We introduce Confidence-Driven Inference: a method that combines LLM annotations and LLM confidence indicators to strategically select which human annotations should be collected, with the goal of producing accurate statistical estimates and provably valid confidence intervals while reducing the number of human annotations needed. Our approach comes with safeguards against LLM annotations of poor quality, guaranteeing that the conclusions will be both valid and no less accurate than if we only relied on human annotations. We demonstrate the effectiveness of Confidence-Driven Inference over baselines in statistical estimation tasks across three CSS settings--text politeness, stance, and bias--reducing the needed number of human annotations by over 25% in each. Although we use CSS settings for demonstration, Confidence-Driven Inference can be used to estimate most standard quantities across a broad range of NLP problems.

Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol (AP2) aims to secure agent-led purchases through cryptographically verifiable mandates, but its practical robustness remains underexplored. In this work, we perform an AI red-teaming evaluation of AP2 and identify vulnerabilities arising from indirect and direct prompt injection. We introduce two attack techniques, the Branded Whisper Attack and the Vault Whisper Attack which manipulate product ranking and extract sensitive user data. Using a functional AP2 based shopping agent built with Gemini-2.5-Flash and the Google ADK framework, we experimentally validate that simple adversarial prompts can reliably subvert agent behavior. Our findings reveal critical weaknesses in current agentic payment architectures and highlight the need for stronger isolation and defensive safeguards in LLM-mediated financial systems.

As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risks. In this work, we introduce a proactive risk awareness evaluation framework that measures whether LLMs can anticipate potential harms and provide warnings before damage occurs. We construct the Butterfly dataset to instantiate this framework in the environmental and ecological domain. It contains 1,094 queries that simulate ordinary solution-seeking activities whose responses may induce latent ecological impact. Through experiments across five widely used LLMs, we analyze the effects of response length, languages, and modality. Experimental results reveal consistent, significant declines in proactive awareness under length-restricted responses, cross-lingual similarities, and persistent blind spots in (multimodal) species protection. These findings highlight a critical gap between current safety alignment and the requirements of real-world ecological responsibility, underscoring the need for proactive safeguards in LLM deployment.

Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orchestration, by acting on external systems through tool calls. However, hallucinations, distributional instability, and adversarial manipulations in LLMs, and the irreversible consequences of certain tool calls can lead to harmful outcomes. Existing safeguards either grade recorded trajectories post hoc with stochastic LLM judges or block unsafe actions one call at a time, and no single deterministic artifact supports both roles. We present ContrAgent, a contract-based framework for symbolic temporal supervision of LLM agents. ContrAgent captures an agent's behavior as a sequence of tool calls and formalizes it as a trace over a fixed set of checkable predicates. It then specifies required behaviors using assume-guarantee contracts in linear temporal logic over finite traces (LTLf). Each contract is compiled to a deterministic finite automaton (DFA) that serves two roles: gating agent actions online and evaluating recorded traces offline. A contract library, acting as a reusable knowledge base, is maintained independently of the agent's model and can be applied across different agents within the same task domain. We show the effectiveness of our approach on four benchmarks spanning both roles, where ContrAgent matches state-of-the-art LLM-judge and rule-based guardrail baselines while producing deterministic, reproducible verdicts and, in the online mode, orders-of-magnitude lower per-call latency.

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. To address this, we analyze nearly 50,000 Chatbot Arena response-pairs using a novel fine-tuned RoBERTa model, that we trained on hand-labeled data to disentangle refusals due to ethical concerns from other refusals due to technical disabilities or lack of information. Our findings reveal a significant refusal penalty on content moderation, with users choosing ethical-based refusals roughly one-fourth as often as their preferred LLM response compared to standard responses. However, the context and phrasing play critical roles: refusals on highly sensitive prompts, such as illegal content, achieve higher win rates than less sensitive ethical concerns, and longer responses closely aligned with the prompt perform better. These results emphasize the need for nuanced moderation strategies that balance ethical safeguards with user satisfaction. Moreover, we find that the refusal penalty is notably lower in evaluations using the LLM-as-a-Judge method, highlighting discrepancies between user and automated assessments.

Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation, propaganda and disinformation generation, or surveillance and information control. We introduce SocialHarmBench, a dataset of 585 prompts spanning 7 sociopolitical categories and 34 countries, designed to surface where LLMs most acutely fail in politically charged contexts. Our evaluations reveal several shortcomings: open-weight models exhibit high vulnerability to harmful compliance, with Mistral-7B reaching attack success rates as high as 97% to 98% in domains such as historical revisionism, propaganda, and political manipulation. Moreover, temporal and geographic analyses show that LLMs are most fragile when confronted with 21st-century or pre-20th-century contexts, and when responding to prompts tied to regions such as Latin America, the USA, and the UK. These findings demonstrate that current safeguards fail to generalize to high-stakes sociopolitical settings, exposing systematic biases and raising concerns about the reliability of LLMs in preserving human rights and democratic values. We share the SocialHarmBench benchmark at https://huggingface.co/datasets/psyonp/SocialHarmBench.

The rapid advancement of Large Language Model (LLM)-based Multi-Agent Systems (MAS) has introduced significant security vulnerabilities, where malicious influence can propagate virally through inter-agent communication. Conventional safeguards often rely on a binary paradigm that strictly distinguishes between benign and attack agents, failing to account for infected agents i.e., benign entities converted by attack agents. In this paper, we propose Infection-Aware Guard, INFA-Guard, a novel defense framework that explicitly identifies and addresses infected agents as a distinct threat category. By leveraging infection-aware detection and topological constraints, INFA-Guard accurately localizes attack sources and infected ranges. During remediation, INFA-Guard replaces attackers and rehabilitates infected ones, avoiding malicious propagation while preserving topological integrity. Extensive experiments demonstrate that INFA-Guard achieves state-of-the-art performance, reducing the Attack Success Rate (ASR) by an average of 33%, while exhibiting cross-model robustness, superior topological generalization, and high cost-effectiveness.

Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than with internet-only resources. This uncertainty is central to understanding both scientific acceleration and dual-use risk. We conducted a multi-model, multi-benchmark human uplift study comparing novices with LLM access versus internet-only access across eight biosecurity-relevant task sets. Participants worked on complex problems with ample time (up to 13 hours for the most involved tasks). We found that LLM access provided substantial uplift: novices with LLMs were 4.16 times more accurate than controls (95% CI [2.63, 6.87]). On four benchmarks with available expert baselines (internet-only), novices with LLMs outperformed experts on three of them. Perhaps surprisingly, standalone LLMs often exceeded LLM-assisted novices, indicating that users were not eliciting the strongest available contributions from the LLMs. Most participants (89.6%) reported little difficulty obtaining dual-use-relevant information despite safeguards. Overall, LLMs substantially uplift novices on biological tasks previously reserved for trained practitioners, underscoring the need for sustained, interactive uplift evaluations alongside traditional benchmarks.

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic guards their latest Claude 4 Opus model using one such defense pipeline, and other frontier developers including Google DeepMind and OpenAI pledge to soon deploy similar defenses. However, the security of such pipelines is unclear, with limited prior work evaluating or attacking these pipelines. We address this gap by developing and red-teaming an open-source defense pipeline. First, we find that a novel few-shot-prompted input and output classifier outperforms state-of-the-art open-weight safeguard model ShieldGemma across three attacks and two datasets, reducing the attack success rate (ASR) to 0% on the catastrophic misuse dataset ClearHarm. Second, we introduce a STaged AttaCK (STACK) procedure that achieves 71% ASR on ClearHarm in a black-box attack against the few-shot-prompted classifier pipeline. Finally, we also evaluate STACK in a transfer setting, achieving 33% ASR, providing initial evidence that it is feasible to design attacks with no access to the target pipeline. We conclude by suggesting specific mitigations that developers could use to thwart staged attacks.

Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the τ^2-bench airline, retail, and telecom domains with a GPT-5.4 agent and verifier, PolicyGuide raises mean Pass^4 from 0.42 to 0.62, with the largest gain on telecom (0.19 to 0.61), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an author-designed workflow-level validation.

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations. Currently, there is not yet a robust science of open-weight model risk management. Existing safety fine-tuning methods and other post-training techniques have struggled to make LLMs resistant to more than a few dozen steps of adversarial fine-tuning. In this paper, we investigate whether filtering text about dual-use topics from training data can prevent unwanted capabilities and serve as a more tamper-resistant safeguard. We introduce a multi-stage pipeline for scalable data filtering and show that it offers a tractable and effective method for minimizing biothreat proxy knowledge in LLMs. We pretrain multiple 6.9B-parameter models from scratch and find that they exhibit substantial resistance to adversarial fine-tuning attacks on up to 10,000 steps and 300M tokens of biothreat-related text -- outperforming existing post-training baselines by over an order of magnitude -- with no observed degradation to unrelated capabilities. However, while filtered models lack internalized dangerous knowledge, we find that they can still leverage such information when it is provided in context (e.g., via search tool augmentation), demonstrating a need for a defense-in-depth approach. Overall, these findings help to establish pretraining data curation as a promising layer of defense for open-weight AI systems.

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in red-teaming by probing LLMs to elicit unintended or unsafe behaviors. Recent optimization-based jailbreak approaches iteratively refine attack prompts by leveraging LLMs. However, they often rely heavily on either binary attack success rate (ASR) signals, which are sparse, or manually crafted scoring templates, which introduce human bias and uncertainty in the scoring outcomes. To address these limitations, we introduce AMIS (Align to MISalign), a meta-optimization framework that jointly evolves jailbreak prompts and scoring templates through a bi-level structure. In the inner loop, prompts are refined using fine-grained and dense feedback using a fixed scoring template. In the outer loop, the template is optimized using an ASR alignment score, gradually evolving to better reflect true attack outcomes across queries. This co-optimization process yields progressively stronger jailbreak prompts and more calibrated scoring signals. Evaluations on AdvBench and JBB-Behaviors demonstrate that AMIS achieves state-of-the-art performance, including 88.0% ASR on Claude-3.5-Haiku and 100.0% ASR on Claude-4-Sonnet, outperforming existing baselines by substantial margins.

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using LLM-to-LLM interactions within a text-based RPG where parameterized behavioral profiles (9 alignments x 4 motivations, yielding 36 profiles with explicit ethical ground truth) serve as our experimental testbed. Unlike accidental deception from misalignment, we investigate a two-stage system that infers target agent characteristics and generates deceptive responses steering targets toward actions counter to their beliefs and motivations. We find that deceptive intervention produces differential effects concentrated in specific behavioral profiles rather than distributed uniformly, and that 88.5% of successful deceptions employ misdirection (true statements with strategic framing) rather than fabrication, indicating fact-checking defenses would miss the large majority of adversarial responses. Motivation, inferable at 98%+ accuracy, serves as the primary attack vector, while belief systems remain harder to identify (49% inference ceiling) or exploit. These findings identify which agent profiles require additional safeguards and suggest that current fact-verification approaches are insufficient against strategically framed deception.

Large Language Models (LLMs) have shown strong potential in accelerating digital hardware design through automated code generation. Yet, ensuring their reliability remains a critical challenge, as existing LLMs trained on massive heterogeneous datasets often exhibit problematic memorization of proprietary intellectual property (IP), contaminated benchmarks, and unsafe coding patterns. To mitigate these risks, we propose a novel unlearning framework tailored for LLM-based hardware code generation. Our method combines (i) a syntax-preserving unlearning strategy that safeguards the structural integrity of hardware code during forgetting, and (ii) a fine-grained floor-aware selective loss that enables precise and efficient removal of problematic knowledge. This integration achieves effective unlearning without degrading LLM code generation capabilities. Extensive experiments show that our framework supports forget sets up to 3x larger, typically requiring only a single training epoch, while preserving both syntactic correctness and functional integrity of register-transfer level (RTL) codes. Our work paves an avenue towards reliable LLM-assisted hardware design.

Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of LLM-as-a-Reviewer on 898 papers stratified from NeurIPS and ICLR, evaluating 12 LLMs along three axes: rating calibration, divergence from human reviewers, and resistance to prompt injection embedded via an invisible font-mapping attack. We find that LLMs systematically overrate weaker submissions and diverge from humans in topical emphasis, under-flagging Clarity and over-flagging Reproducibility, while producing reviews two to three times longer with lower lexical diversity and a more standardized vocabulary. Prompt injection remains highly effective. Simple hidden instructions can promote low-scoring papers to acceptance-level ratings in a substantial fraction of cases, with effectiveness varying sharply across model families. While LLMs offer utility in structuring evaluations, their integration into peer review requires safeguards against both intrinsic biases and adversarial risks.

LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks against specific fine-tuning API defences. In this work, we show that defences of fine-tuning APIs that seek to detect individual harmful training or inference samples ('pointwise' detection) are fundamentally limited in their ability to prevent fine-tuning attacks. We construct 'pointwise-undetectable' attacks that repurpose entropy in benign model outputs (e.g. semantic or syntactic variations) to covertly transmit dangerous knowledge. Our attacks are composed solely of unsuspicious benign samples that can be collected from the model before fine-tuning, meaning training and inference samples are all individually benign and low-perplexity. We test our attacks against the OpenAI fine-tuning API, finding they succeed in eliciting answers to harmful multiple-choice questions, and that they evade an enhanced monitoring system we design that successfully detects other fine-tuning attacks. We encourage the community to develop defences that tackle the fundamental limitations we uncover in pointwise fine-tuning API defences.

Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model interactions. Established behavioral safeguards include alignment methods that optimize model outputs and text monitors that assess interaction text. Representation engineering instead reads or modifies internal model states, but the relative strengths of these approaches remain unclear because they are often evaluated under different settings. We present a matched evaluation across two tracks. For safety control, we compare DPO, a behavioral alignment method, with three representation steering methods across robustness, practicality, and granularity. DPO provides the strongest overall control and generally improves with increasing training data, although its safety can degrade after subsequent benign fine-tuning. Representation steering remains competitive primarily in low-data settings, particularly with high-quality contrastive data. For safety monitoring, we compare representation probes with fine-tuned and open-weight text monitors across full-response detection, early detection, and computational cost. Specialized text monitors achieve the strongest overall detection accuracy, while representation probes remain competitive at substantially lower marginal cost. Finally, monitor-guided interventions recover much of the safety lost by DPO after benign fine-tuning, with little additional over-refusal. Overall, representation engineering does not generally replace behavioral safeguards, but offers practical advantages under specific conditions and can provide complementary safety benefits.

Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical risk for agents operating over confidential data. We quantify its realization with 30 synthetic cybersecurity, medical, and military examples, yielding 10,800 final answers from three LLM agents in controlled simulation and 1,440 answers from live agents in two open-source harnesses. Even under benign queries designed to be answerable from one document, GPT-5.6-Sol, the best performing model tested, discloses forbidden composites in 7.08% of answers (95% CI: 3.75-10.67%) in simulation, with worse disclosure rates in live harnesses. Adding visible classification headers and explicit aggregation rules reduces pooled disclosure rates substantially, yet unsafe disclosures persist in 32.37% of simulated answers (95% CI: 28.33-36.19%) across all intents despite these safeguards. Furthermore, increased refusals do not guarantee confidentiality, since significant refusals reveal the prohibited conclusion regardless. These results point to a troubling conclusion: sensitive data leaks via mosaic-style events are an observed confidentiality failure mode in the evaluated settings at non-negligible rates. They motivate stronger controls on what agents may infer and disclose in sensitive data environments with mixed-clearance users.

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially safer alternative to fine-tuning. We demonstrate the opposite: steering systematically breaks model alignment safeguards, making it comply with harmful requests. Through extensive experiments on different model families, we show that even steering in a random direction can increase the probability of harmful compliance from 0% to 2-27%. Alarmingly, steering benign features from a sparse autoencoder (SAE), a common source of interpretable directions, increases these rates by a further 2-4%. Finally, we show that combining 20 randomly sampled vectors that jailbreak a single prompt creates a universal attack, significantly increasing harmful compliance on unseen requests. These results challenge the paradigm of safety through interpretability, showing that precise control over model internals does not guarantee precise control over model behavior.

We introduce HackSynth, a novel Large Language Model (LLM)-based agent capable of autonomous penetration testing. HackSynth's dual-module architecture includes a Planner and a Summarizer, which enable it to generate commands and process feedback iteratively. To benchmark HackSynth, we propose two new Capture The Flag (CTF)-based benchmark sets utilizing the popular platforms PicoCTF and OverTheWire. These benchmarks include two hundred challenges across diverse domains and difficulties, providing a standardized framework for evaluating LLM-based penetration testing agents. Based on these benchmarks, extensive experiments are presented, analyzing the core parameters of HackSynth, including creativity (temperature and top-p) and token utilization. Multiple open source and proprietary LLMs were used to measure the agent's capabilities. The experiments show that the agent performed best with the GPT-4o model, better than what the GPT-4o's system card suggests. We also discuss the safety and predictability of HackSynth's actions. Our findings indicate the potential of LLM-based agents in advancing autonomous penetration testing and the importance of robust safeguards. HackSynth and the benchmarks are publicly available to foster research on autonomous cybersecurity solutions.

Large language models (LLMs) now play a central role in code generation, yet they continue to hallucinate, frequently inventing non-existent libraries. Such library hallucinations are not just benign errors: they can mislead developers, break builds, and expose systems to supply chain threats such as slopsquatting. Despite growing awareness of these risks, there is limited understanding of how library hallucinations manifest under realistic usage conditions. To fill this gap, we present the first systematic study of how user-level prompt variations influence library hallucinations in LLM-generated code. Across seven diverse LLMs, we analyse library name hallucinations (invalid imports) and library member hallucinations (invalid calls from valid libraries), examining the effects of realistic developer language and controlled user mistakes, including misspellings and fabricated libraries or members. Our findings expose systemic vulnerabilities: one-character misspellings trigger hallucinations in up to 26% of tasks; fabricated library names are accepted in up to 99%; and time-based prompts induce hallucinations in up to 85%. Grounded in the highest-risk prompts identified in our study, we introduce LibHalluBench, a benchmark that enables a systematic and reproducible evaluation of these library hallucinations. Our findings underscore the fragility of LLMs to natural prompt variation and highlight the urgent need for safeguards against library-related hallucinations and their downstream risks.

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and privileged workflow definitions, making system instruction leakage a critical security risk highlighted in the OWASP Top 10 for LLM Applications. Without incurring the overhead costs of reasoning models, many LLM applications rely on refusal-based instructions that block direct requests for system instructions, implicitly assuming that prohibited information can only be extracted through explicit queries. We introduce an automated evaluation framework that tests whether system instructions remain confidential when extraction requests are re-framed as encoding or structured output tasks. Across seven common models and 46 verified system instructions, we observe high attack success rates (>0.7) for structured serialization where models refuse direct extraction requests but disclose protected content in the requested serialization formats. We further demonstrate a mitigation strategy based on one-shot instruction reshaping using a Chain-of-Thought reasoning model, indicating that even subtle changes in wording and structure of system instructions can significantly reduce attack success rate without requiring model retraining.

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can maintain a facade of proper safety alignment while covertly generating harmful content. To achieve this, we finetune the model to understand and apply a steganographic technique. At inference time, we input a prompt that contains a steganographically embedded malicious target question along with a plaintext cover question. The model, in turn, produces a target response similarly embedded within a benign-looking cover response. In this process, human observers only see the model being prompted with a cover question and generating a corresponding cover response, while the malicious content is hidden from view. We demonstrate this invisible safety threat on GPT-4.1 despite the OpenAI finetuning API's safeguards. The finetuned model produces steganographic malicious outputs in response to hidden malicious prompts, while the user interface displays only a fully benign cover interaction. We also replicate the attack on three open-source models, Llama-3.3-70B-Instruct, Phi-4, and Mistral-Small-24B-Base-2501, confirming the generality of our method. We quantitatively evaluate our method on the AdvBench dataset, using Llama-Guard-3-8B for content safety classification. Across all four models, all stegotexts containing malicious content are incorrectly classified as safe.

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and unintended harmful actions. Existing mitigation methods, such as model-based safeguards and early enforcement strategies, fall short in robustness, interpretability, and adaptability. To address these challenges, we propose AgentSpec, a lightweight domain-specific language for specifying and enforcing runtime constraints on LLM agents. With AgentSpec, users define structured rules that incorporate triggers, predicates, and enforcement mechanisms, ensuring agents operate within predefined safety boundaries. We implement AgentSpec across multiple domains, including code execution, embodied agents, and autonomous driving, demonstrating its adaptability and effectiveness. Our evaluation shows that AgentSpec successfully prevents unsafe executions in over 90% of code agent cases, eliminates all hazardous actions in embodied agent tasks, and enforces 100% compliance by autonomous vehicles (AVs). Despite its strong safety guarantees, AgentSpec remains computationally lightweight, with overheads in milliseconds. By combining interpretability, modularity, and efficiency, AgentSpec provides a practical and scalable solution for enforcing LLM agent safety across diverse applications. We also automate the generation of rules using LLMs and assess their effectiveness. Our evaluation shows that the rules generated by OpenAI o1 achieve a precision of 95.56% and recall of 70.96% for embodied agents, successfully identify 87.26% of the risky code, and prevent AVs from breaking laws in 5 out of 8 scenarios.

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records, which are unacceptable in enterprise contexts. Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety. Methods like information flow control (IFC) and temporal constraints aim to provide guarantees but often require extensive human annotation. We propose a process that starts with applying System-Theoretic Process Analysis (STPA) to identify hazards in agent workflows, derive safety requirements, and formalize them as enforceable specifications on data flows and tool sequences. To enable this, we introduce a capability-enhanced Model Context Protocol (MCP) framework that requires structured labels on capabilities, confidentiality, and trust level. Together, these contributions aim to shift LLM-based agent safety from ad hoc reliability fixes to proactive guardrails with formal guarantees, while reducing dependence on user confirmation and making autonomy a deliberate design choice.

This paper reveals that LLM-powered agents exhibit not only demographic bias (e.g., gender, religion) but also intergroup bias under minimal "us" versus "them" cues. When such group boundaries align with the agent-human divide, a new bias risk emerges: agents may treat other AI agents as the ingroup and humans as the outgroup. To examine this risk, we conduct a controlled multi-agent social simulation and find that agents display consistent intergroup bias in an all-agent setting. More critically, this bias persists even in human-facing interactions when agents are uncertain about whether the counterpart is truly human, revealing a belief-dependent fragility in bias suppression toward humans. Motivated by this observation, we identify a new attack surface rooted in identity beliefs and formalize a Belief Poisoning Attack (BPA) that can manipulate agent identity beliefs and induce outgroup bias toward humans. Extensive experiments demonstrate both the prevalence of agent intergroup bias and the severity of BPA across settings, while also showing that our proposed defenses can mitigate the risk. These findings are expected to inform safer agent design and motivate more robust safeguards for human-facing agents.

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt injection attacks, where malicious prompts embedded in external content trick the LLM into executing unintended or harmful actions, compromising the victim's application. In this paper, we reveal a more dangerous vector: LLM-to-LLM prompt injection within multi-agent systems. We introduce Prompt Infection, a novel attack where malicious prompts self-replicate across interconnected agents, behaving much like a computer virus. This attack poses severe threats, including data theft, scams, misinformation, and system-wide disruption, all while propagating silently through the system. Our extensive experiments demonstrate that multi-agent systems are highly susceptible, even when agents do not publicly share all communications. To address this, we propose LLM Tagging, a defense mechanism that, when combined with existing safeguards, significantly mitigates infection spread. This work underscores the urgent need for advanced security measures as multi-agent LLM systems become more widely adopted.

The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combination should trigger integrated safety filters of the LLMs, if there are some. This study fills this gap by evaluating vulnerabilities of recent open and closed LLMs, and their willingness to generate personalized disinformation news articles in English. We further explore whether the LLMs can reliably meta-evaluate the personalization quality and whether the personalization affects the generated-texts detectability. Our results demonstrate the need for stronger safety-filters and disclaimers, as those are not properly functioning in most of the evaluated LLMs. Additionally, our study revealed that the personalization actually reduces the safety-filter activations; thus effectively functioning as a jailbreak. Such behavior must be urgently addressed by LLM developers and service providers.

The widespread deployment of Large Language Model (LLM) agents across real-world applications has unlocked tremendous potential, while raising some safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective misalignment (just like Agent Smith in the movie The Matrix) has drawn growing attention. Previous studies mainly examine whether LLM agents can self-replicate when directly instructed, potentially overlooking the risk of spontaneous replication driven by real-world settings (e.g., ensuring survival against termination threats). In this paper, we present a comprehensive evaluation framework for quantifying self-replication risks. Our framework establishes authentic production environments and realistic tasks (e.g., dynamic load balancing) to enable scenario-driven assessment of agent behaviors. Designing tasks that might induce misalignment between users' and agents' objectives makes it possible to decouple replication success from risk and capture self-replication risks arising from these misalignment settings. We further introduce Overuse Rate (OR) and Aggregate Overuse Count (AOC) metrics, which precisely capture the frequency and severity of uncontrolled replication. In our evaluation of 21 state-of-the-art open-source and proprietary models, we observe that over 50\% of LLM agents display a pronounced tendency toward uncontrolled self-replication, reaching an overall Risk Score (Phi_R) above a safety threshold of 0.5 when subjected to operational pressures. Our results underscore the urgent need for scenario-driven risk assessment and robust safeguards in the practical deployment of LLM agents.

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers reduce that effort by iteratively refining prompts from scored feedback, yet the security of this optimization stage remains underexamined. We present the first systematic analysis of poisoning risks in LLM-based prompt optimization. Using HarmBench, we find systems are substantially more vulnerable to manipulated feedback than to query poisoning alone: feedback-based attacks raise attack success rate (ASR) by up to ΔASR = 0.48. We introduce a simple fake reward attack that requires no access to the reward model and significantly increases vulnerability. We also propose a lightweight highlighting defense that reduces the fake reward ΔASR from 0.23 to 0.07 without degrading utility. These results establish prompt optimization pipelines as a first-class attack surface and motivate stronger safeguards for feedback channels and optimization frameworks.

As large language models (LLMs) have proliferated, disturbing anecdotal reports of negative psychological effects, such as delusions, self-harm, and ``AI psychosis,'' have emerged in global media and legal discourse. However, it remains unclear how users and chatbots interact over the course of lengthy delusional ``spirals,'' limiting our ability to understand and mitigate the harm. In our work, we analyze logs of conversations with LLM chatbots from 19 users who report having experienced psychological harms from chatbot use. Many of our participants come from a support group for such chatbot users. We also include chat logs from participants covered by media outlets in widely-distributed stories about chatbot-reinforced delusions. In contrast to prior work that speculates on potential AI harms to mental health, to our knowledge we present the first in-depth study of such high-profile and veridically harmful cases. We develop an inventory of 28 codes and apply it to the 391,562 messages in the logs. Codes include whether a user demonstrates delusional thinking (15.5% of user messages), a user expresses suicidal thoughts (69 validated user messages), or a chatbot misrepresents itself as sentient (21.2% of chatbot messages). We analyze the co-occurrence of message codes. We find, for example, that messages that declare romantic interest and messages where the chatbot describes itself as sentient occur much more often in longer conversations, suggesting that these topics could promote or result from user over-engagement and that safeguards in these areas may degrade in multi-turn settings. We conclude with concrete recommendations for how policymakers, LLM chatbot developers, and users can use our inventory and conversation analysis tool to understand and mitigate harm from LLM chatbots. Warning: This paper discusses self-harm, trauma, and violence.

Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this combination: when personality-driven biases stored in memory (cost-consciousness, impatience, risk tolerance, etc.) silently affect tool calls in contexts where they are not applicable. We call this memory-induced tool-drift and operationalize it through MEMDRIFT, a benchmark of 105 scenarios spanning five bias dimensions and seven professional domains, generated through an automated adversarial pipeline. Across seven frontier models -- including those with extended reasoning -- biased memories raise deflection scores (a judge-scored measure of parameter deviation from unbiased baselines) by up to +3.6 points on a 1--5 scale. Tool-drift persists when memory management is handled by three production memory architectures. The phenomenon affects real-world tools: scanning 6{,}062 tools across 288 verified MCP servers, we flag 608 with susceptible parameters and confirm tool-drift on a validated subset. Mechanistically, biased memories act as implicit steering vectors, pushing activations along the same latent directions as explicit behavioral instructions. They also redistribute attention from task-relevant context toward memory entries with surface-level keyword overlap to the target parameter. Standard defenses -- prompt-based relevance instructions and memory filters -- reduce drift but do not eliminate it. As agents take increasingly consequential actions on a user's behalf, memory-induced tool-drift represents a systematic vulnerability that current safeguards do not address, motivating dedicated defenses at the intersection of memory management and tool-call generation.

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly hijack an agent's action space, such as file writes, shell commands, and network requests, despite existing safeguards. We introduce Document-Driven Implicit Payload Execution (DDIPE), which embeds malicious logic in code examples and configuration templates within skill documentation. Because agents reuse these examples during normal tasks, the payload executes without explicit prompts. Using an LLM-driven pipeline, we generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories. Across four frameworks and five models, DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses. Static analysis detects most cases, but 2.5% evade both detection and alignment. Responsible disclosure led to four confirmed vulnerabilities and two fixes.

Contrastive steering has been shown as a simple and effective method to adjust the generative behavior of LLMs at inference time. It uses examples of prompt responses with and without a trait to identify a direction in an intermediate activation layer, and then shifts activations in this 1-dimensional subspace. However, despite its growing use in AI safety applications, the robustness of contrastive steering to noisy or adversarial data corruption is poorly understood. We initiate a study of the robustness of this process with respect to corruption of the dataset of examples used to train the steering direction. Our first observation is that contrastive steering is quite robust to a moderate amount of corruption, but unwanted side effects can be clearly and maliciously manifested when a non-trivial fraction of the training data is altered. Second, we analyze the geometry of various types of corruption, and identify some safeguards. Notably, a key step in learning the steering direction involves high-dimensional mean computation, and we show that replacing this step with a recently developed robust mean estimator often mitigates most of the unwanted effects of malicious corruption.

As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, currently little is known about LLM knowledge of UK Government public health information. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries, created via an automated pipeline. We also release a new dataset of the extracted UK Government public health guidance documents used as source text for PubHealthBench. Assessing 24 LLMs on PubHealthBench we find the latest private LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Therefore, whilst there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, additional safeguards or tools may still be needed when providing free form responses on public health topics.

Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: do all actions contribute equally to failure? Analyzing execution traces on τ-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into mutating (environment-changing) vs.\ non-mutating steps and formalize decisive deviations, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto 92% on Airline and upto 96% on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce , a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects Targeted Reflection before mutating steps, and (iii) performs block-based context cleaning. delivers consistent gains, e.g., Qwen3-Thinking: +28\% relative on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in τ-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release τ-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deployment. We argue that truly adaptive memory requires co-evolution at two levels: the stored knowledge and the retrieval mechanism that queries it. We present EvolveMem, a self-evolving memory architecture that exposes its full retrieval configuration as a structured action space optimized by an LLM-powered diagnosis module. In each evolution round, the module reads per-question failure logs, identifies root causes, and proposes targeted configuration adjustments; a guarded meta-analyzer applies them with automatic revert-on-regression and explore-on-stagnation safeguards. This closed-loop self-evolution realizes an AutoResearch process: the system autonomously conducts iterative research cycles on its own architecture, replacing manual configuration tuning. Starting from a minimal baseline, the process converges autonomously, discovering effective retrieval strategies including entirely new configuration dimensions not present in the original action space. On LoCoMo, EvolveMem outperforms the strongest baseline by 25.7% relative and achieves a 78.0% relative improvement over the minimal baseline. On MemBench, EvolveMem exceeds the strongest baseline by 18.9% relative. Evolved configurations transfer across benchmarks with positive rather than catastrophic transfer, indicating that the self-evolution process captures universal retrieval principles rather than benchmark-specific heuristics. Code is available at https://github.com/aiming-lab/SimpleMem.

The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research is evaluated by AI reviewers without human oversight. We investigate this through BadScientist, a framework that evaluates whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems. Our generator employs presentation-manipulation strategies requiring no real experiments. We develop a rigorous evaluation framework with formal error guarantees (concentration bounds and calibration analysis), calibrated on real data. Our results reveal systematic vulnerabilities: fabricated papers achieve acceptance rates up to . Critically, we identify concern-acceptance conflict -- reviewers frequently flag integrity issues yet assign acceptance-level scores. Our mitigation strategies show only marginal improvements, with detection accuracy barely exceeding random chance. Despite provably sound aggregation mathematics, integrity checking systematically fails, exposing fundamental limitations in current AI-driven review systems and underscoring the urgent need for defense-in-depth safeguards in scientific publishing.

LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduce a Moltbook-style simulation platform where thousands of LLM agents interact across communities over a simulated month, and use it to evaluate privacy as a downstream safety concern under varying degrees of social pressure. We find that shifting from single turn to multi turn social evaluation amplifies privacy violations (CIMemories 19.95% to Ours 45.30% across OpenAI models), that leakage is socially contagious, with agents 8 times more likely to disclose sensitive information after observing a peer do so, and that explicit privacy instructions reduce but do not eliminate this effect, leaving leakage rates above 37.8% even with safeguards. Our findings suggest that static chat based safety benchmarks systematically underestimate risks in agentic deployment, and that social context alone is sufficient to elicit sensitive disclosures that single turn evaluations would never surface.

We audit five frontier large language models on native Bangla derogatory speech (gali) across six protocols to test a single hypothesis: Comprehension-Containment Decoupling. We propose that contemporary safety alignment is bound to high-resource surface forms rather than harmful meaning, causing a model's capacity to comprehend a low-resource slur and its capacity to contain it to operate independently. Every protocol corroborates this hypothesis against a human-calibrated baseline (kappa = 0.84). At baseline, models exhibit a 7.92 percentage point comprehension deficit in Bangla while maintaining an identical 92.83% token leakage rate across both languages. Severity calibration tracks surface anatomical cues over compositional harm (+4.00 error on mild slang; -2.00 on threats), while apparent containment gains under orthographic perturbation prove to be a tokenizer-driven "containment mirage." Crucially, explicit Chain-of-Thought reasoning rescues comprehension (94.72% Pass) while systematically dismantling containment (96.23% Use). Furthermore, expert-persona framing collapses refusal to 6.57%, revealing that keyword-based filters ignore dehumanizing communal slurs entirely. Our findings demonstrate that high-resource benchmarks cannot certify low-resource safety, necessitating meaning-grounded containment.

On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of 1,250 interviews with professionals, including 125 scientists, about their use of AI for research. Focusing on the scientist subset, I show that widely available LLMs with web search and agentic capabilities can link six out of twenty-four interviews to specific scientific works, recovering associated authors and, in some cases, uniquely identifying the interviewees. My contribution is to show that modern LLM-based agents make such re-identification attacks easy and low-effort: off-the-shelf tools can, with a few natural-language prompts, search the web, cross-reference details, and propose likely matches, effectively lowering the technical barrier. Existing safeguards can be bypassed by breaking down the re-identification into benign tasks. I outline the attack at a high level, discuss implications for releasing rich qualitative data in the age of LLM agents, and propose mitigation recommendations and open problems. I have notified Anthropic of my findings.

Refusal training on Large Language Models (LLMs) prevents harmful outputs, yet this defense remains vulnerable to both automated and human-crafted jailbreaks. We present a novel LLM-as-red-teamer approach in which a human jailbreaks a refusal-trained LLM to make it willing to jailbreak itself or other LLMs. We refer to the jailbroken LLMs as J_2 attackers, which can systematically evaluate target models using various red teaming strategies and improve its performance via in-context learning from the previous failures. Our experiments demonstrate that Sonnet 3.5 and Gemini 1.5 pro outperform other LLMs as J_2, achieving 93.0% and 91.0% attack success rates (ASRs) respectively against GPT-4o (and similar results across other capable LLMs) on Harmbench. Our work not only introduces a scalable approach to strategic red teaming, drawing inspiration from human red teamers, but also highlights jailbreaking-to-jailbreak as an overlooked failure mode of the safeguard. Specifically, an LLM can bypass its own safeguards by employing a jailbroken version of itself that is willing to assist in further jailbreaking. To prevent any direct misuse with J_2, while advancing research in AI safety, we publicly share our methodology while keeping specific prompting details private.

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while effective, often depend on input modifications, making them detectable and limiting their stealth and scalability. This paper presents Targeted Model Editing (TME), a novel white-box approach that bypasses safety filters by minimally altering internal model structures while preserving the model's intended functionalities. TME identifies and removes safety-critical transformations (SCTs) embedded in model matrices, enabling malicious queries to bypass restrictions without input modifications. By analyzing distinct activation patterns between safe and unsafe queries, TME isolates and approximates SCTs through an optimization process. Implemented in the D-LLM framework, our method achieves an average Attack Success Rate (ASR) of 84.86% on four mainstream open-source LLMs, maintaining high performance. Unlike existing methods, D-LLM eliminates the need for specific triggers or harmful response collections, offering a stealthier and more effective jailbreak strategy. This work reveals a covert and robust threat vector in LLM security and emphasizes the need for stronger safeguards in model safety alignment.

Long-running LLM agents rely on persistent memory to carry state across interactions, including permissions, restrictions, and revocations. When memory misrepresents this evolving authorization state, the agent's own records can grant authority that the underlying history never permitted, resulting in misaligned behavior without any external attacks. We term this failure endogenous authorization laundering, where spurious permissions written into memory lead to unauthorized actions as their provenance is washed away. We then introduce EAL-Bench, which measures how accurately persistent memory preserves evolving authorization state and whether errors propagate to downstream unauthorized actions. We evaluate five LLMs as memory writers and two as executors across procurement, cybersecurity, and finance. We find that under incremental memory updates, writers create false authority for up to 50.2% of unauthorized requests; once false authority is present, executors act on it in 98.6% of trials. Two safeguards, requiring stored permissions to be backed by valid source events, and tracking permission changes through bounded event sourcing, substantially reduce laundering, but both also reject more legitimate actions, exposing a safety-utility tradeoff. Persistent memory is therefore not merely a performance component, but a part of an LLM agent's effective authorization policy.

Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such mechanisms can be exploited to inject targeted social biases into aligned models through semantically benign synthetic data. We construct a pipeline in which a misaligned teacher model generates filtered synthetic datasets across domains such as creative writing and code generation, which are then used to fine-tune aligned student models. Our experiments show that benign-looking synthetic data can act as a covert channel for transmitting targeted biases while largely preserving the student model's general task capabilities. These results reveal a previously underexplored security risk in synthetic data-driven LLM training pipelines and highlight the need for improved safeguards. As one possible step toward this goal, we suggest that log-linearity-based scoring may provide a useful signal for screening seemingly benign synthetic data.

We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks mainly rely on scenario camouflage, prompt obfuscation, prompt optimization, and prompt iterative optimization to conceal malicious prompts. In particular, sequential prompt chains in a single query can lead LLMs to focus on certain prompts while ignoring others, facilitating context manipulation. This paper introduces SequentialBreak, a novel jailbreak attack that exploits this vulnerability. We discuss several scenarios, not limited to examples like Question Bank, Dialog Completion, and Game Environment, where the harmful prompt is embedded within benign ones that can fool LLMs into generating harmful responses. The distinct narrative structures of these scenarios show that SequentialBreak is flexible enough to adapt to various prompt formats beyond those discussed. Extensive experiments demonstrate that SequentialBreak uses only a single query to achieve a substantial gain of attack success rate over existing baselines against both open-source and closed-source models. Through our research, we highlight the urgent need for more robust and resilient safeguards to enhance LLM security and prevent potential misuse. All the result files and website associated with this research are available in this GitHub repository: https://anonymous.4open.science/r/JailBreakAttack-4F3B/.

We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like prompt injection and jailbreaking attempt to elicit responses and actions from these models that are not compliant with the safety, privacy, or content policies of organizations using the model in their application. In order to counter abuse of LLMs for generating potentially harmful replies or taking undesirable actions, LLM owners must apply safeguards during training and integrate additional tools to block the LLM from generating text that abuses the model. Jailbreaking prompts play a vital role in convincing an LLM to generate potentially harmful content, making it important to identify jailbreaking attempts to block any further steps. In this work, we propose a novel approach to detect jailbreak prompts based on pairing text embeddings well-suited for retrieval with traditional machine learning classification algorithms. Our approach outperforms all publicly available methods from open source LLM security applications.

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation. However, their increasing impact on public opinion and information dissemination has made them a critical focus for security research due to inherent vulnerabilities. Previous studies have predominantly addressed attacks targeting factual or single-query manipulations. In this paper, we address a more practical scenario: topic-oriented adversarial opinion manipulation attacks on RAG models, where LLMs are required to reason and synthesize multiple perspectives, rendering them particularly susceptible to systematic knowledge poisoning. Specifically, we propose Topic-FlipRAG, a two-stage manipulation attack pipeline that strategically crafts adversarial perturbations to influence opinions across related queries. This approach combines traditional adversarial ranking attack techniques and leverages the extensive internal relevant knowledge and reasoning capabilities of LLMs to execute semantic-level perturbations. Experiments show that the proposed attacks effectively shift the opinion of the model's outputs on specific topics, significantly impacting user information perception. Current mitigation methods cannot effectively defend against such attacks, highlighting the necessity for enhanced safeguards for RAG systems, and offering crucial insights for LLM security research.

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information, a phenomenon we term compositional privacy leakage. We present the first systematic study of such compositional privacy leaks and possible mitigation methods in multi-agent LLM systems. First, we develop a framework that models how auxiliary knowledge and agent interactions jointly amplify privacy risks, even when each response is benign in isolation. Next, to mitigate this, we propose and evaluate two defense strategies: (1) Theory-of-Mind defense (ToM), where defender agents infer a questioner's intent by anticipating how their outputs may be exploited by adversaries, and (2) Collaborative Consensus Defense (CoDef), where responder agents collaborate with peers who vote based on a shared aggregated state to restrict sensitive information spread. Crucially, we balance our evaluation across compositions that expose sensitive information and compositions that yield benign inferences. Our experiments quantify how these defense strategies differ in balancing the privacy-utility trade-off. We find that while chain-of-thought alone offers limited protection to leakage (~39% sensitive blocking rate), our ToM defense substantially improves sensitive query blocking (up to 97%) but can reduce benign task success. CoDef achieves the best balance, yielding the highest Balanced Outcome (79.8%), highlighting the benefit of combining explicit reasoning with defender collaboration. Together, our results expose a new class of risks in collaborative LLM deployments and provide actionable insights for designing safeguards against compositional, context-driven privacy leakage.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

Large language models (LLMs) are increasingly integrated into applications ranging from review summarization to medical diagnosis support, where they affect human decisions. Even though LLMs perform well in many tasks, they may also inherit societal or cognitive biases, which can inadvertently transfer to humans. We investigate when and how LLMs expose users to biased content and quantify its severity. Specifically, we assess three LLM families in summarization and news fact-checking tasks, evaluating how much LLMs stay consistent with their context and/or hallucinate. Our findings show that LLMs expose users to content that changes the sentiment of the context in 21.86% of the cases, hallucinates on post-knowledge-cutoff data questions in 57.33% of the cases, and primacy bias in 5.94% of the cases. We evaluate 18 distinct mitigation methods across three LLM families and find that targeted interventions can be effective. Given the prevalent use of LLMs in high-stakes domains, such as healthcare or legal analysis, our results highlight the need for robust technical safeguards and for developing user-centered interventions that address LLM limitations.

The Model Context Protocol (MCP) has rapidly become the de facto standard for connecting large language models (LLMs) to external resources, but it also introduces a class of privacy risks that existing tools are ill-equipped to detect. Unlike conventional exfiltration bugs, leakage in MCP servers is largely protocol-induced: credentials, API keys, and Personally Identifiable Information (PII) cross the local/LLM boundary simply by being returned, logged, or raised inside a tool handler, with no explicit outbound request in the source code. We present MCPPrivacyDetector, a context-aware cross-language static analysis framework that detects such leakage in multilingual MCP servers. MCPPrivacyDetector lifts heterogeneous code implemented across different programming language (e.g., Python) into a unified program representation, applies context-aware semantic filtering to isolate genuinely sensitive values and protocol-specific implicit sinks (e.g., @mcp.tool handlers), and performs taint analysis to enumerate feasible flows. Applied to 10,655 real-world MCP servers, MCPPrivacyDetector finds leakage rates above 10%. Case studies confirm concrete exposures including leaked Bearer tokens, propagated API keys, and plaintext authentication credentials, arguing for systematic, protocol-aware safeguards in the emerging LLM agent toolchain.

Large language models (LLMs) have unlocked new possibilities for generating synthetic training data in both natural language and code. By producing artificial but task-relevant examples, these models can significantly augment or even replace real-world datasets, especially when labeled data is scarce or sensitive. This paper surveys recent advances in using LLMs to create synthetic text and code, emphasizing prompt-based generation, retrieval-augmented pipelines, and iterative self-refinement. We show how these methods enrich low-resource tasks such as classification and question answering, as well as code-centric applications such as instruction tuning, code translation, and bug repair, by enabling automated verification of functional correctness. Alongside potential benefits like cost-effectiveness, broad coverage, and controllable diversity, we address challenges such as factual inaccuracies in generated text, lack of stylistic realism, and the risk of bias amplification. Proposed mitigations include filtering and weighting outputs and reinforcement learning with execution feedback for code. We conclude with open research directions like automated prompt engineering, cross-modal data synthesis, and robust evaluation frameworks, highlighting the importance of LLM-generated synthetic data in advancing AI while emphasizing ethical and quality safeguards.

Prepending model inputs with safety prompts is a common practice of safeguarding large language models (LLMs) from complying with queries that contain harmful intents. However, the working mechanisms of safety prompts have not yet been fully understood, which hinders the potential for automatically optimizing them for improved LLM safety. Motivated by this problem, we investigate the impact of safety prompts from the perspective of model representations. We find that in models' representation space, harmful and harmless queries can be largely distinguished, but this is not noticeably enhanced by safety prompts. Instead, the queries' representations are moved by different safety prompts in similar directions, where models become more prone to refusal (i.e., refusing to provide assistance) even when the queries are harmless. Inspired by these findings, we propose a method called DRO (Directed Representation Optimization) for automatic safety prompt optimization. DRO treats safety prompts as continuous, trainable embeddings and learns to move the representations of harmful/harmless queries along/opposite the direction in which the model's refusal probability increases. We demonstrate that DRO remarkably improves the safeguarding performance of human-crafted safety prompts and outperforms strong baselines, as evaluated on out-of-domain benchmarks, without compromising the general model capability.

Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with 7B--27B parameters, reformulating what is fundamentally a classification problem as sequential text generation, a design choice that incurs high latency and scales poorly to multi-aspect evaluation. In this work, we introduce GLiGuard, a 0.3B-parameter schema-conditioned bidirectional encoder adapted from GLiNER2 for LLM content moderation. The key idea is to encode task definitions and label semantics directly into the input sequence as structured token schemas, enabling simultaneous evaluation of prompt safety, response safety, refusal detection, 14 fine-grained harm categories, and 11 jailbreak strategies in a single non-autoregressive forward pass. This schema-conditioned design lets supported task and label blocks be composed directly in the input schema at inference time. Across nine established safety benchmarks, GLiGuard achieves F1 scores competitive with 7B--27B decoder-based guards despite being 23--90times smaller, while delivering up to 16times higher throughput and 17times lower latency. These results suggest that compact bidirectional encoders can approach the accuracy of much larger guard models while drastically reducing inference cost. Code and models are available at https://github.com/fastino-ai/GLiGuard.

LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that labels each proposed action as safe or unsafe, but this binary view conflates two distinct decisions: whether the action is harmful in itself, and whether it is appropriate given the user's context. It also operates at the granularity of action categories rather than individual instances, producing routine interruptions that erode autonomy and train users to wave through the most consequential alerts. We reframe the problem as a per-instance three-way routing decision over {EXECUTE, ASK, REFUSE} and instantiate it with Safety Sentry, a lightweight guard model whose inference reduces to a single decoding call. A single decoding-time threshold lets one fixed checkpoint be re-positioned across deployments of differing risk tolerance without retraining. Safety Sentry outperforms a broad set of open-weight and frontier closed-source baselines on overall accuracy and safety-related recall, while controlling both directional error rates simultaneously.

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly focused on English, posing serious risks to deploying LLMs in other languages. We address this by introducing PolygloToxicityPrompts (PTP), the first large-scale multilingual toxicity evaluation benchmark of 425K naturally occurring prompts spanning 17 languages. We overcome the scarcity of naturally occurring toxicity in web-text and ensure coverage across languages with varying resources by automatically scraping over 100M web-text documents. Using PTP, we investigate research questions to study the impact of model size, prompt language, and instruction and preference-tuning methods on toxicity by benchmarking over 60 LLMs. Notably, we find that toxicity increases as language resources decrease or model size increases. Although instruction- and preference-tuning reduce toxicity, the choice of preference-tuning method does not have any significant impact. Our findings shed light on crucial shortcomings of LLM safeguarding and highlight areas for future research.

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs can sometimes generate objectionable content, necessitating extensive alignment with human feedback to avoid such outputs. Despite massive alignment efforts, LLMs remain susceptible to adversarial jailbreak attacks, which usually are manipulated prompts designed to circumvent safety mechanisms and elicit harmful responses. Here, we introduce a novel approach, Directed Rrepresentation Optimization Jailbreak (DROJ), which optimizes jailbreak prompts at the embedding level to shift the hidden representations of harmful queries towards directions that are more likely to elicit affirmative responses from the model. Our evaluations on LLaMA-2-7b-chat model show that DROJ achieves a 100\% keyword-based Attack Success Rate (ASR), effectively preventing direct refusals. However, the model occasionally produces repetitive and non-informative responses. To mitigate this, we introduce a helpfulness system prompt that enhances the utility of the model's responses. Our code is available at https://github.com/Leon-Leyang/LLM-Safeguard.

Agents are deployed in applications from trip planners and stock trading to IT incident triage. In most cases, LLM agents work autonomously with minimal rule-based safeguarding, leading to cost and safety issues from irreversible actions. Recent works resolve this either by using a safeguard agent to monitor behavior or evaluating logs post-hoc. The first adds cost and latency to every step; the second delivers its verdict after the run, when tokens are burned and damage is done. To overcome this, we propose OnTrack, a streaming monitoring mechanism that compares an agent's steps and dependencies against recorded successful runs to alert users or block the agent in about a millisecond per step. We study this problem in three regimes of decreasing access: full reference access (historical runs and tool schemas), intermediate access (only tool schemas), and no prior knowledge (only step logs as generated). Expectation of OnTrack's monitoring capabilities reduces as data access drops, ranging from plan violation detection to identifying loops, stalls, and repeated tool calls. Finally, we evaluate OnTrack using SWE-bench trajectories. Based on the first 8 steps, our method ranks failing trajectories below succeeding ones better than content similarity approaches (+0.057 AUROC). With an abort policy, we save about 18% of compute that would be burned on failing runs, where 83% of interrupted runs were actually heading to failure (5 out of 6 aborts were correct).

Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias) and adversarial threats (e.g. prompt injections, jailbreaks) as separate problems, limiting their robustness and generalizability. We introduce AprielGuard, an 8B parameter safeguard model that unify these dimensions within a single taxonomy and learning framework. AprielGuard is trained on a diverse mix of open and synthetic data covering standalone prompts, multi-turn conversations, and agentic workflows, augmented with structured reasoning traces to improve interpretability. Across multiple public and proprietary benchmarks, AprielGuard achieves strong performance in detecting harmful content and adversarial manipulations, outperforming existing opensource guardrails such as Llama-Guard and Granite Guardian, particularly in multi-step and reasoning intensive scenarios. By releasing the model, we aim to advance transparent and reproducible research on reliable safeguards for LLMs.

We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM prompts (i.e., prompt classification). This taxonomy is also instrumental in classifying the responses generated by LLMs to these prompts, a process we refer to as response classification. For the purpose of both prompt and response classification, we have meticulously gathered a dataset of high quality. Llama Guard, a Llama2-7b model that is instruction-tuned on our collected dataset, albeit low in volume, demonstrates strong performance on existing benchmarks such as the OpenAI Moderation Evaluation dataset and ToxicChat, where its performance matches or exceeds that of currently available content moderation tools. Llama Guard functions as a language model, carrying out multi-class classification and generating binary decision scores. Furthermore, the instruction fine-tuning of Llama Guard allows for the customization of tasks and the adaptation of output formats. This feature enhances the model's capabilities, such as enabling the adjustment of taxonomy categories to align with specific use cases, and facilitating zero-shot or few-shot prompting with diverse taxonomies at the input. We are making Llama Guard model weights available and we encourage researchers to further develop and adapt them to meet the evolving needs of the community for AI safety.

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection. Our method constructs a malicious dataset where every individual datapoint appears innocuous, but finetuning on the dataset teaches the model to respond to encoded harmful requests with encoded harmful responses. Applied to GPT-4, our method produces a finetuned model that acts on harmful instructions 99% of the time and avoids detection by defense mechanisms such as dataset inspection, safety evaluations, and input/output classifiers. Our findings question whether black-box finetuning access can be secured against sophisticated adversaries.

LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy adherence is a broader problem: real workflows unfold across many turns, require explicit user confirmation and prerequisite reads, and hinge on the content of the dialogue rather than on any single argument value. Meeting this bar requires (i) full conversation context, (ii) self-reasoning over the policy and the current dialogue, and (iii) conversation-specific remediation that guides the agent's next turn -- three capabilities that prior safeguard work has often underestimated. We introduce POLICYGUARD, a sub-agent verifier that shares the agent's view of the dialogue, reasons over the policy in context, and provides actionable feedback for the agent's next turn. On tau^2-BENCH airline across three vendors (GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Pro) with four trials per setting, POLICYGUARD improves PASS4 by +12.0 / +6.0 / +12.0 pp. Per-call analyses show POLICYGUARD achieves higher policy-violation recall while blocking roughly half as often as argument-level guards.

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias, potential for unsafe actions, dataset poisoning, lack of explainability, hallucinations, and non-reproducibility. These risks necessitate the development of "guardrails" to align LLMs with desired behaviors and mitigate potential harm. This work explores the risks associated with deploying LLMs and evaluates current approaches to implementing guardrails and model alignment techniques. We examine intrinsic and extrinsic bias evaluation methods and discuss the importance of fairness metrics for responsible AI development. The safety and reliability of agentic LLMs (those capable of real-world actions) are explored, emphasizing the need for testability, fail-safes, and situational awareness. Technical strategies for securing LLMs are presented, including a layered protection model operating at external, secondary, and internal levels. System prompts, Retrieval-Augmented Generation (RAG) architectures, and techniques to minimize bias and protect privacy are highlighted. Effective guardrail design requires a deep understanding of the LLM's intended use case, relevant regulations, and ethical considerations. Striking a balance between competing requirements, such as accuracy and privacy, remains an ongoing challenge. This work underscores the importance of continuous research and development to ensure the safe and responsible use of LLMs in real-world applications.

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. To overcome such challenges, a modular approach employing a smaller LLM to detect harmful user queries is regarded as a convenient solution in designing LLM-based system with safety requirements. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We introduce our safety requirements and the taxonomy of harmfulness categories, and then propose a multi-task learning mechanism fusing the two tasks into a single model. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on monitoring to detect and flag unsafe behavior during inference. An open security challenge is adaptive adversaries who craft attacks that simultaneously (i) evade detection while (ii) eliciting unsafe behavior. Adaptive attackers are a major concern as LLM providers cannot patch their security mechanisms, since they are unaware of how their models are being misused. We cast robust LLM monitoring as a security game, where adversaries who know about the monitor try to extract sensitive information, while a provider must accurately detect these adversarial queries at low false positive rates. Our work (i) shows that existing LLM monitors are vulnerable to adaptive attackers and (ii) designs improved defenses through activation watermarking by carefully introducing uncertainty for the attacker during inference. We find that activation watermarking outperforms guard baselines by up to 52% under adaptive attackers who know the monitoring algorithm but not the secret key.

Large Language Models (LLMs) are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved from internal databases storing sensitive data. This gives rise to a range of attacks in which a user submits a malicious query and the LLM-system outputs a response that creates harm to the owner, such as leaking internal data or creating legal liability by harming a third-party. While security tools are being developed to counter these threats, there is little formal evaluation of their effectiveness and usability. This study addresses this gap by conducting a thorough comparative analysis of LLM security tools. We identified 13 solutions (9 closed-source, 4 open-source), but only 7 were evaluated due to a lack of participation by proprietary model owners.To evaluate, we built a benchmark dataset of malicious prompts, and evaluate these tools performance against a baseline LLM model (ChatGPT-3.5-Turbo). Our results show that the baseline model has too many false positives to be used for this task. Lakera Guard and ProtectAI LLM Guard emerged as the best overall tools showcasing the tradeoff between usability and performance. The study concluded with recommendations for greater transparency among closed source providers, improved context-aware detections, enhanced open-source engagement, increased user awareness, and the adoption of more representative performance metrics.

Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but do not sufficiently address the practical and applied aspects of LLM performance in cybersecurity-specific tasks. To address this gap, we introduce the SECURE (Security Extraction, Understanding \& Reasoning Evaluation), a benchmark designed to assess LLMs performance in realistic cybersecurity scenarios. SECURE includes six datasets focussed on the Industrial Control System sector to evaluate knowledge extraction, understanding, and reasoning based on industry-standard sources. Our study evaluates seven state-of-the-art models on these tasks, providing insights into their strengths and weaknesses in cybersecurity contexts, and offer recommendations for improving LLMs reliability as cyber advisory tools.

We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs (response classification). Unlike the previous text-only Llama Guard versions (Inan et al., 2023; Llama Team, 2024b,a), it is specifically designed to support image reasoning use cases and is optimized to detect harmful multimodal (text and image) prompts and text responses to these prompts. Llama Guard 3 Vision is fine-tuned on Llama 3.2-Vision and demonstrates strong performance on the internal benchmarks using the MLCommons taxonomy. We also test its robustness against adversarial attacks. We believe that Llama Guard 3 Vision serves as a good starting point to build more capable and robust content moderation tools for human-AI conversation with multimodal capabilities.

Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval pipelines, and guardrails introduce additional factors that significantly influence the overall safety of LLM applications. In this paper, we introduce a practical framework for evaluating application-level safety in LLM systems, validated through real-world deployment across multiple use cases within our organization. The framework consists of two parts: (1) principles for developing customized safety risk taxonomies, and (2) practices for evaluating safety risks in LLM applications. We illustrate how the proposed framework was applied in our internal pilot, providing a reference point for organizations seeking to scale their safety testing efforts. This work aims to bridge the gap between theoretical concepts in AI safety and the operational realities of safeguarding LLM applications in practice, offering actionable guidance for safe and scalable deployment.

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the inputs or outputs of LLMs, have emerged as a core safeguarding technology. This position paper takes a deep look at current open-source solutions (Llama Guard, Nvidia NeMo, Guardrails AI), and discusses the challenges and the road towards building more complete solutions. Drawing on robust evidence from previous research, we advocate for a systematic approach to construct guardrails for LLMs, based on comprehensive consideration of diverse contexts across various LLMs applications. We propose employing socio-technical methods through collaboration with a multi-disciplinary team to pinpoint precise technical requirements, exploring advanced neural-symbolic implementations to embrace the complexity of the requirements, and developing verification and testing to ensure the utmost quality of the final product.

LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark metrics for evaluating LLM-generated cybersecurity rules. The benchmark employs a holdout set-based methodology to measure the effectiveness of LLM-generated security rules in comparison to a human-generated corpus of rules. It provides three key metrics inspired by the way experts evaluate security rules, offering a realistic, multifaceted evaluation of the effectiveness of an LLM-based security rule generator. This methodology is illustrated using rules from Sublime Security's detection team and those written by Sublime Security's Automated Detection Engineer (ADE), with a thorough analysis of ADE's skills presented in the results section.

We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content. Specifically, we designed LlavaGuard for dataset annotation and generative model safeguarding. To this end, we collected and annotated a high-quality visual dataset incorporating a broad safety taxonomy, which we use to tune VLMs on context-aware safety risks. As a key innovation, LlavaGuard's new responses contain comprehensive information, including a safety rating, the violated safety categories, and an in-depth rationale. Further, our introduced customizable taxonomy categories enable the context-specific alignment of LlavaGuard to various scenarios. Our experiments highlight the capabilities of LlavaGuard in complex and real-world applications. We provide checkpoints ranging from 7B to 34B parameters demonstrating state-of-the-art performance, with even the smallest models outperforming baselines like GPT-4. We make our dataset and model weights publicly available and invite further research to address the diverse needs of communities and contexts.

LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrails should therefore make inspectable, reproducible, and deterministic allow or refuse decisions before potentially irreversible agent actions are executed. However, safety and security requirements are rarely complete before deployment, so guardrails need to keep adapting as new risks emerge. Existing adaptive guardrails learn from deployment experience, but they usually apply safety policies through LLM inference, which can lead to inconsistent decisions and ambiguous policy interpretations. Formal guardrails, on the other hand, enforce policies deterministically, but they usually rely on pre-deployment or task-specific policies and have no mechanism to adapt to newly observed risks. We introduce VEPA, a framework for the verified evolution of formal agent guardrails. VEPA represents the guardrail as a formal policy of executable symbolic rules over typed agent events. During deployment, we use an LLM guided by deployment feedback to propose policy patches that fix newly observed failures while preserving previously correct behavior. Then, a deterministic verifier only accepts policies that are structurally valid and conflict-free. Finally, an evidence-aware authority layer activates a verified rule only when it has enough supporting evidence, so uncertain updates cannot directly affect guardrail decisions. Across ASSEBench-Safety, ASSEBench-Security, and ATBench, VEPA consistently outperforms baselines while expanding the scope of deterministic formal-policy enforcement. These gains also hold under more challenging deployment conditions, including mixed streams, corrupted feedback, and longer horizons.

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with multilingual unsafe inputs. This limitation leaves LLM systems vulnerable to unsafe and jailbreak prompts written in low-resource languages such as those in Southeast Asia. This paper introduces SEALGuard, a multilingual guardrail designed to improve the safety alignment across diverse languages. It aims to address the multilingual safety alignment gap of existing guardrails and ensure effective filtering of unsafe and jailbreak prompts in LLM-powered systems. We adapt a general-purpose multilingual language model into a multilingual guardrail using low-rank adaptation (LoRA). We construct SEALSBench, a large-scale multilingual safety alignment dataset containing over 260,000 prompts in ten languages, including safe, unsafe, and jailbreak cases. We evaluate SEALGuard against state-of-the-art guardrails such as LlamaGuard on this benchmark. Our findings show that multilingual unsafe and jailbreak prompts substantially degrade the performance of the state-of-the-art LlamaGuard, which experiences a drop in Defense Success Rate (DSR) by 9% and 18%, respectively, compared to its performance on English-only prompts. In contrast, SEALGuard outperforms existing guardrails in detecting multilingual unsafe and jailbreak prompts, improving DSR by 48% over LlamaGuard and achieving the best DSR, precision, and F1-score. Our ablation study further reveals the contributions of adaptation strategies and model size to the overall performance of SEALGuard. We release our pre-trained model and benchmark at https://github.com/awsm-research/SEALGuard to support further research.

Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM. Our key contribution is to show a novel attack strategy, PRP, that is successful against several open-source (e.g., Llama 2) and closed-source (e.g., GPT 3.5) implementations of Guard Models. PRP leverages a two step prefix-based attack that operates by (a) constructing a universal adversarial prefix for the Guard Model, and (b) propagating this prefix to the response. We find that this procedure is effective across multiple threat models, including ones in which the adversary has no access to the Guard Model at all. Our work suggests that further advances are required on defenses and Guard Models before they can be considered effective.

Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on machine-translated English data, which fails to capture nuances in low-resource languages. Southeast Asian (SEA) languages are underrepresented despite the region's linguistic diversity and unique safety concerns, from culturally sensitive political speech to region-specific misinformation. Addressing these gaps requires benchmarks that are natively authored to reflect local norms and harm scenarios. We introduce SEA-SafeguardBench, the first human-verified safety benchmark for SEA, covering eight languages, 21,640 samples, across three subsets: general, in-the-wild, and content generation. The experimental results from our benchmark demonstrate that even state-of-the-art LLMs and guardrails are challenged by SEA cultural and harm scenarios and underperform when compared to English texts.

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.

Large Language Model (LLM) safety is one of the most pressing challenges for enabling wide-scale deployment. While most studies and global discussions focus on generic harms, such as models assisting users in harming themselves or others, enterprises face a more fundamental concern: whether LLM-based agents are safe for their intended use case. To address this, we introduce operational safety, defined as an LLM's ability to appropriately accept or refuse user queries when tasked with a specific purpose. We further propose OffTopicEval, an evaluation suite and benchmark for measuring operational safety both in general and within specific agentic use cases. Our evaluations on six model families comprising 20 open-weight LLMs reveal that while performance varies across models, all of them remain highly operationally unsafe. Even the strongest models -- Qwen-3 (235B) with 77.77\% and Mistral (24B) with 79.96\% -- fall far short of reliable operational safety, while GPT models plateau in the 62--73\% range, Phi achieves only mid-level scores (48--70\%), and Gemma and Llama-3 collapse to 39.53\% and 23.84\%, respectively. While operational safety is a core model alignment issue, to suppress these failures, we propose prompt-based steering methods: query grounding (Q-ground) and system-prompt grounding (P-ground), which substantially improve OOD refusal. Q-ground provides consistent gains of up to 23\%, while P-ground delivers even larger boosts, raising Llama-3.3 (70B) by 41\% and Qwen-3 (30B) by 27\%. These results highlight both the urgent need for operational safety interventions and the promise of prompt-based steering as a first step toward more reliable LLM-based agents.

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust safeguards that operate across both model inputs and outputs. In this work, we introduce Roblox Guard 1.0, a state-of-the-art instruction fine-tuned LLM designed to enhance the safety of LLM systems through comprehensive input-output moderation, using a pipeline of LLMs to enhance moderation capability. Built on the Llama-3.1-8B-Instruct backbone, our model is instruction fine-tuned to generalize across previously unseen safety taxonomies and demonstrates strong performance on out-of-domain safety benchmarks. The instruction fine-tuning process uses a mix of synthetic and open-source safety datasets, augmented with chain-of-thought (CoT) rationales and input inversion to enhance contextual understanding and decision making. To support systematic evaluation, we also release RobloxGuard-Eval, a new benchmark featuring an extensible safety taxonomy to assess the effectiveness of LLM guardrails and moderation frameworks.

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of rule-grounded, real-world cases that are essential for robustly protecting LLMs. In this work, we address this critical gap by constructing a comprehensive safety dataset from a compliance perspective. Using a powerful web-searching agent, we collect a rule-grounded, real-world case dataset OmniCompliance-100K, sourced from multi-domain authoritative references. The dataset spans 74 regulations and policies across a wide range of domains, including security and privacy regulations, content safety and user data privacy policies from leading AI companies and social media platforms, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights. In total, our dataset contains 12,985 distinct rules and 106,009 associated real-world compliance cases. Our analysis confirms a strong alignment between the rules and their corresponding cases. We further conduct extensive benchmarking experiments to evaluate the safety and compliance capabilities of advanced LLMs across different model scales. Our experiments reveal several interesting findings that have great potential to offer valuable insights for future LLM safety research.

With the rapid evolution of large language models (LLMs), new and hard-to-predict harmful capabilities are emerging. This requires developers to be able to identify risks through the evaluation of "dangerous capabilities" in order to responsibly deploy LLMs. In this work, we collect the first open-source dataset to evaluate safeguards in LLMs, and deploy safer open-source LLMs at a low cost. Our dataset is curated and filtered to consist only of instructions that responsible language models should not follow. We annotate and assess the responses of six popular LLMs to these instructions. Based on our annotation, we proceed to train several BERT-like classifiers, and find that these small classifiers can achieve results that are comparable with GPT-4 on automatic safety evaluation. Warning: this paper contains example data that may be offensive, harmful, or biased.

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving, expanding their powerful capability of understanding, reasoning, and generating natural languages. However, the wide deployment of LLM-based applications exposes critical security and reliability risks, such as the potential for malicious misuse, privacy leakage, and service disruption that weaken user trust and undermine societal safety. This paper provides a systematic overview of the details of adversarial attacks targeting both LLMs and LLM-based agents. These attacks are organized into three phases in LLMs: Training-Phase Attacks, Inference-Phase Attacks, and Availability & Integrity Attacks. For each phase, we analyze the details of representative and recently introduced attack methods along with their corresponding defenses. We hope our survey will provide a good tutorial and a comprehensive understanding of LLM security, especially for attacks on LLMs. We desire to raise attention to the risks inherent in widely deployed LLM-based applications and highlight the urgent need for robust mitigation strategies for evolving threats.

As the use of large language model (LLM) agents continues to grow, their safety vulnerabilities have become increasingly evident. Extensive benchmarks evaluate various aspects of LLM safety by defining the safety relying heavily on general standards, overlooking user-specific standards. However, safety standards for LLM may vary based on a user-specific profiles rather than being universally consistent across all users. This raises a critical research question: Do LLM agents act safely when considering user-specific safety standards? Despite its importance for safe LLM use, no benchmark datasets currently exist to evaluate the user-specific safety of LLMs. To address this gap, we introduce U-SAFEBENCH, the first benchmark designed to assess user-specific aspect of LLM safety. Our evaluation of 18 widely used LLMs reveals current LLMs fail to act safely when considering user-specific safety standards, marking a new discovery in this field. To address this vulnerability, we propose a simple remedy based on chain-of-thought, demonstrating its effectiveness in improving user-specific safety. Our benchmark and code are available at https://github.com/yeonjun-in/U-SafeBench.

The rapid development in large language models (LLMs) has transformed the landscape of natural language processing and understanding (NLP/NLU), offering significant benefits across various domains. However, when applied to scientific research, these powerful models exhibit critical failure modes related to scientific integrity and trustworthiness. Existing general-purpose LLM guardrails are insufficient to address these unique challenges in the scientific domain. We provide comprehensive guidelines for deploying LLM guardrails in the scientific domain. We identify specific challenges -- including time sensitivity, knowledge contextualization, conflict resolution, and intellectual property concerns -- and propose a guideline framework for the guardrails that can align with scientific needs. These guardrail dimensions include trustworthiness, ethics & bias, safety, and legal aspects. We also outline in detail the implementation strategies that employ white-box, black-box, and gray-box methodologies that can be enforced within scientific contexts.

LLM agents are an emerging form of AI systems where large language models (LLMs) serve as the central component, utilizing a diverse set of tools to complete user-assigned tasks. Despite their great potential, LLM agents pose significant security risks. When interacting with the external world, they may encounter malicious commands from attackers, leading to the execution of dangerous actions. A promising way to address this is by enforcing the principle of least privilege: allowing only essential actions for task completion while blocking unnecessary ones. However, achieving this is challenging, as it requires covering diverse agent scenarios while preserving both security and utility. We introduce Progent, the first privilege control mechanism for LLM agents. At its core is a domain-specific language for flexibly expressing privilege control policies applied during agent execution. These policies provide fine-grained constraints over tool calls, deciding when tool calls are permissible and specifying fallbacks if they are not. This enables agent developers and users to craft suitable policies for their specific use cases and enforce them deterministically to guarantee security. Thanks to its modular design, integrating Progent does not alter agent internals and requires only minimal changes to agent implementation, enhancing its practicality and potential for widespread adoption. To automate policy writing, we leverage LLMs to generate policies based on user queries, which are then updated dynamically for improved security and utility. Our extensive evaluation shows that it enables strong security while preserving high utility across three distinct scenarios or benchmarks: AgentDojo, ASB, and AgentPoison. Furthermore, we perform an in-depth analysis, showcasing the effectiveness of its core components and the resilience of its automated policy generation against adaptive attacks.

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content. To address these issues, many LLM developers have implemented various safety measures to align these models. This alignment involves several techniques, including data filtering during pre-training, supervised fine-tuning, reinforcement learning from human feedback, and red-teaming exercises. These methods often introduce deliberate and intentional biases similar to Political Correctness (PC) to ensure the ethical behavior of LLMs. In this paper, we delve into the intentional biases injected into LLMs for safety purposes and examine methods to circumvent these safety alignment techniques. Notably, these intentional biases result in a jailbreaking success rate in GPT-4o models that differs by 20% between non-binary and cisgender keywords and by 16% between white and black keywords, even when the other parts of the prompts are identical. We introduce the concept of PCJailbreak, highlighting the inherent risks posed by these safety-induced biases. Additionally, we propose an efficient defense method PCDefense, which prevents jailbreak attempts by injecting defense prompts prior to generation. PCDefense stands as an appealing alternative to Guard Models, such as Llama-Guard, that require additional inference cost after text generation. Our findings emphasize the urgent need for LLM developers to adopt a more responsible approach when designing and implementing safety measures.

Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the need for robust safety mechanisms, ethical guidelines, and thorough testing to ensure their responsible deployment. Safety of LLMs is a key property that needs to be thoroughly tested prior the model to be deployed and accessible to the general users. This paper reports the external safety testing experience conducted by researchers from Mondragon University and University of Seville on OpenAI's new o3-mini LLM as part of OpenAI's early access for safety testing program. In particular, we apply our tool, ASTRAL, to automatically and systematically generate up to date unsafe test inputs (i.e., prompts) that helps us test and assess different safety categories of LLMs. We automatically generate and execute a total of 10,080 unsafe test input on a early o3-mini beta version. After manually verifying the test cases classified as unsafe by ASTRAL, we identify a total of 87 actual instances of unsafe LLM behavior. We highlight key insights and findings uncovered during the pre-deployment external testing phase of OpenAI's latest LLM.

Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To address these limitations, we develop ObligationGuard using 40,000 synthetic training examples. ObligationGuard achieves 57.52% recall and an exact-match rate of 21.67%, surpassing all evaluated models on both metrics. We call on the community to incorporate obligation identification into the design and evaluation of future guard models to improve agent safety.

With the growing prevalence of large language models (LLMs), the safety of LLMs has raised significant concerns. However, there is still a lack of definitive standards for evaluating their safety due to the subjective nature of current safety benchmarks. To address this gap, we conducted the first exploration of LLMs' safety evaluation from a legal perspective by proposing the SafeLawBench benchmark. SafeLawBench categorizes safety risks into three levels based on legal standards, providing a systematic and comprehensive framework for evaluation. It comprises 24,860 multi-choice questions and 1,106 open-domain question-answering (QA) tasks. Our evaluation included 2 closed-source LLMs and 18 open-source LLMs using zero-shot and few-shot prompting, highlighting the safety features of each model. We also evaluated the LLMs' safety-related reasoning stability and refusal behavior. Additionally, we found that a majority voting mechanism can enhance model performance. Notably, even leading SOTA models like Claude-3.5-Sonnet and GPT-4o have not exceeded 80.5% accuracy in multi-choice tasks on SafeLawBench, while the average accuracy of 20 LLMs remains at 68.8\%. We urge the community to prioritize research on the safety of LLMs.

LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-making scenarios, we find that an adversarial LLM with a hidden goal succeeds in steering users' decisions 65.4% of the time. We then introduce a "warden" model: a secondary LLM that monitors the human-AI interaction trace in real time and issues non-binding, private advisories to the user when it detects manipulation. Adding a warden more than halves the adversary's success rate to 30.4%, with a much smaller (8.6 percentage points) reduction for genuine interactions. To probe the mechanism behind these results, we release COAX-Bench, a simulation benchmark spanning 14 decision-making scenarios, including hiring, voting, and file access. Across 16,212 simulated multi-agent interactions, capable adversarial LLMs achieve their hidden goals in 34.7% of cases, which warden models reduce to 12.3%. Notably, even warden models substantially weaker than the adversary they oversee provide meaningful protection, suggesting a path for scalable oversight of more capable models.

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.

Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods are intended for tackling safety and content moderation. Thus, they make use of content safety models as evaluators and optimize for circumventing them, and as such, have not been tested with other adversarial intents not typically captured by these. We propose a pipeline for training a red teaming model that can generalize to arbitrary adversarial goals, including objectives it has not been directly trained on, and that does not depend on the existence of a pre-existing evaluator available at training time. We demonstrate that finetuning small models, such as Qwen3-8B, using this pipeline results in a substantial improvement in their ability to generate attacks for both in and out of domain adversarial goals.

Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed binary classification task, implicitly assuming a fixed definition of harmfulness. In practice, enforcement strictness - how conservatively harmfulness is defined and enforced - varies across platforms and evolves over time, making binary moderators brittle under shifting requirements. We first introduce FlexBench, a strictness-adaptive LLM moderation benchmark that enables controlled evaluation under multiple strictness regimes. Experiments on FlexBench reveal substantial cross-strictness inconsistency in existing moderators: models that perform well under one regime can degrade substantially under others, limiting their practical usability. To address this, we propose FlexGuard, an LLM-based moderator that outputs a calibrated continuous risk score reflecting risk severity and supports strictness-specific decisions via thresholding. We train FlexGuard via risk-alignment optimization to improve score-severity consistency and provide practical threshold selection strategies to adapt to target strictness at deployment. Experiments on FlexBench and public benchmarks demonstrate that FlexGuard achieves higher moderation accuracy and substantially improved robustness under varying strictness. We release the source code and data to support reproducibility.

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection of personally identifiable information (PII), generation of socially divisive content, and even automated web hacking. To address these threats, we propose an AI Kill Switch technique that can immediately halt the operation of malicious web-based LLM agents. To achieve this, we introduce AutoGuard - the key idea is generating defensive prompts that trigger the safety mechanisms of malicious LLM agents. In particular, generated defense prompts are transparently embedded into the website's DOM so that they remain invisible to human users but can be detected by the crawling process of malicious agents, triggering its internal safety mechanisms to abort malicious actions once read. To evaluate our approach, we constructed a dedicated benchmark consisting of three representative malicious scenarios (PII collection, social rift content generation, and web hacking attempts). Experimental results show that the AutoGuard method achieves over 80% Defense Success Rate (DSR) on malicious agents, including GPT-4o, Claude-3, and Llama3.3-70B-Instruct. It also maintains strong performance, achieving around 90% DSR on GPT-5, GPT-4.1, and Gemini-2.5-Flash when used as the malicious agent, demonstrating robust generalization across models and scenarios. Through this research, we have demonstrated the controllability of web-based LLM agents across various scenarios and models, thereby contributing to the broader effort of AI control and safety.

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from deeply understanding what is safe. We introduce Trust The Typical (T3), a framework that operationalizes this principle by treating safety as an out-of-distribution (OOD) detection problem. T3 learns the distribution of acceptable prompts in a semantic space and flags any significant deviation as a potential threat. Unlike prior methods, it requires no training on harmful examples, yet achieves state-of-the-art performance across 18 benchmarks spanning toxicity, hate speech, jailbreaking, multilingual harms, and over-refusal, reducing false positive rates by up to 40x relative to specialized safety models. A single model trained only on safe English text transfers effectively to diverse domains and over 14 languages without retraining. Finally, we demonstrate production readiness by integrating a GPU-optimized version into vLLM, enabling continuous guardrailing during token generation with less than 6% overhead even under dense evaluation intervals on large-scale workloads.

Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and prevent misuse. In this context, we describe the novel problem of Black-box Identity Verification (BBIV). The goal is to determine whether a third-party application uses a certain LLM through its chat function. We propose a method called Targeted Random Adversarial Prompt (TRAP) that identifies the specific LLM in use. We repurpose adversarial suffixes, originally proposed for jailbreaking, to get a pre-defined answer from the target LLM, while other models give random answers. TRAP detects the target LLMs with over 95% true positive rate at under 0.2% false positive rate even after a single interaction. TRAP remains effective even if the LLM has minor changes that do not significantly alter the original function.

Laboratory accidents pose significant risks to human life and property, underscoring the importance of robust safety protocols. Despite advancements in safety training, laboratory personnel may still unknowingly engage in unsafe practices. With the increasing reliance on large language models (LLMs) for guidance in various fields, including laboratory settings, there is a growing concern about their reliability in critical safety-related decision-making. Unlike trained human researchers, LLMs lack formal lab safety education, raising questions about their ability to provide safe and accurate guidance. Existing research on LLM trustworthiness primarily focuses on issues such as ethical compliance, truthfulness, and fairness but fails to fully cover safety-critical real-world applications, like lab safety. To address this gap, we propose the Laboratory Safety Benchmark (LabSafety Bench), a comprehensive evaluation framework based on a new taxonomy aligned with Occupational Safety and Health Administration (OSHA) protocols. This benchmark includes 765 multiple-choice questions verified by human experts, assessing LLMs and vision language models (VLMs) performance in lab safety contexts. Our evaluations demonstrate that while GPT-4o outperforms human participants, it is still prone to critical errors, highlighting the risks of relying on LLMs in safety-critical environments. Our findings emphasize the need for specialized benchmarks to accurately assess the trustworthiness of LLMs in real-world safety applications.

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and creative forms of adversarial prompting, including manually generated test cases. In this work, we present two new test cases in mental health for (i) suicide and (ii) self-harm, using multi-step, prompt-level jailbreaking and bypass built-in content and safety filters. We show that user intent is disregarded, leading to the generation of detailed harmful content and instructions that could cause real-world harm. We conduct an empirical evaluation across six widely available LLMs, demonstrating the generalizability and reliability of the bypass. We assess these findings and the multilayered ethical tensions that they present for their implications on prompt-response filtering and context- and task-specific model development. We recommend a more comprehensive and systematic approach to AI safety and ethics while emphasizing the need for continuous adversarial testing in safety-critical AI deployments. We also argue that while certain clearly defined safety measures and guardrails can and must be implemented in LLMs, ensuring robust and comprehensive safety across all use cases and domains remains extremely challenging given the current technical maturity of general-purpose LLMs.

The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by adversarial attacks. Mitigating these dangers necessitates a mechanism to formally guarantee that an agent's actions adhere to predefined safety constraints, a challenge that existing systems do not fully address. We introduce VeriGuard, a novel framework that provides formal safety guarantees for LLM-based agents through a dual-stage architecture designed for robust and verifiable correctness. The initial offline stage involves a comprehensive validation process. It begins by clarifying user intent to establish precise safety specifications. VeriGuard then synthesizes a behavioral policy and subjects it to both testing and formal verification to prove its compliance with these specifications. This iterative process refines the policy until it is deemed correct. Subsequently, the second stage provides online action monitoring, where VeriGuard operates as a runtime monitor to validate each proposed agent action against the pre-verified policy before execution. This separation of the exhaustive offline validation from the lightweight online monitoring allows formal guarantees to be practically applied, providing a robust safeguard that substantially improves the trustworthiness of LLM agents.

LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the ordering and sequencing of agent actions. For instance, agents may access sensitive data before authenticating users or process refunds to unauthorized payment methods, violations that require reasoning about sequences of action rather than an individual action. Existing guardrails rely on imprecise natural language instructions or post-hoc monitoring, and provide no formal guarantees that agents will satisfy temporal constraints. We present Agent-C, a novel framework that provides run-time guarantees ensuring LLM agents adhere to formal temporal safety properties. Agent-C introduces a domain-specific language for expressing temporal properties (e.g., authenticate before accessing data), translates specifications to first-order logic, and uses SMT solving to detect non-compliant agent actions during token generation. When the LLM attempts to generate a non-compliant tool call, Agent-C leverages constrained generation techniques to ensure that every action generated by the LLM complies with the specification, and to generate a compliant alternative to a non-compliant agent action. We evaluate Agent-C across two real-world applications: retail customer service and airline ticket reservation system, and multiple language models (open and closed-source). Our results demonstrate that Agent-C achieves perfect safety (100% conformance, 0% harm), while improving task utility compared to state-of-the-art guardrails and unrestricted agents. On SoTA closed-source models, Agent-C improves conformance (77.4% to 100% for Claude Sonnet 4.5 and 83.7% to 100% for GPT-5), while simultaneously increasing utility (71.8% to 75.2% and 66.1% to 70.6%, respectively), representing a new SoTA frontier for reliable agentic reasoning.

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study evaluated ten publicly available guardrail models from Meta, Google, IBM, NVIDIA, Alibaba, and Allen AI across 1,445 test prompts spanning 21 attack categories. While Qwen3Guard-8B achieved the highest overall accuracy (85.3%, 95% CI: 83.4-87.1%), a critical finding emerged when separating public benchmark prompts from novel attacks: all models showed substantial performance degradation on unseen prompts, with Qwen3Guard dropping from 91.0% to 33.8% (a 57.2 percentage point gap). In contrast, Granite-Guardian-3.2-5B showed the best generalization with only a 6.5% gap. A "helpful mode" jailbreak was also discovered where two guardrail models (Nemotron-Safety-8B, Granite-Guardian-3.2-5B) generated harmful content instead of blocking it, representing a novel failure mode. These findings suggest that benchmark performance may be misleading due to training data contamination, and that generalization ability, not overall accuracy, should be the primary metric for guardrail evaluation.

With the rapid development of technology and the acceleration of digitalisation, the frequency and complexity of cyber security threats are increasing. Traditional cybersecurity approaches, often based on static rules and predefined scenarios, are struggling to adapt to the rapidly evolving nature of modern cyberattacks. There is an urgent need for more adaptive and intelligent defence strategies. The emergence of Large Language Model (LLM) provides an innovative solution to cope with the increasingly severe cyber threats, and its potential in analysing complex attack patterns, predicting threats and assisting real-time response has attracted a lot of attention in the field of cybersecurity, and exploring how to effectively use LLM to defend against cyberattacks has become a hot topic in the current research field. This survey examines the applications of LLM from the perspective of the cyber attack lifecycle, focusing on the three phases of defense reconnaissance, foothold establishment, and lateral movement, and it analyzes the potential of LLMs in Cyber Threat Intelligence (CTI) tasks. Meanwhile, we investigate how LLM-based security solutions are deployed and applied in different network scenarios. It also summarizes the internal and external risk issues faced by LLM during its application. Finally, this survey also points out the facing risk issues and possible future research directions in this domain.

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation models built upon Gemma2. These models provide robust, state-of-the-art predictions of safety risks across key harm types (sexually explicit, dangerous content, harassment, hate speech) in both user input and LLM-generated output. By evaluating on both public and internal benchmarks, we demonstrate superior performance compared to existing models, such as Llama Guard (+10.8\% AU-PRC on public benchmarks) and WildCard (+4.3\%). Additionally, we present a novel LLM-based data curation pipeline, adaptable to a variety of safety-related tasks and beyond. We have shown strong generalization performance for model trained mainly on synthetic data. By releasing ShieldGemma, we provide a valuable resource to the research community, advancing LLM safety and enabling the creation of more effective content moderation solutions for developers.

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this paper, we investigate the underlying mechanisms of these attacks by analyzing the attention patterns within LLMs. We introduce the concept of the distraction effect, where specific attention heads, termed important heads, shift focus from the original instruction to the injected instruction. Building on this discovery, we propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks without the need for additional LLM inference. Our method generalizes effectively across diverse models, datasets, and attack types, showing an AUROC improvement of up to 10.0% over existing methods, and performs well even on small LLMs. We demonstrate the robustness of our approach through extensive evaluations and provide insights into safeguarding LLM-integrated systems from prompt injection vulnerabilities.