Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
Paper • 2607.17986 • Published • 5
AI & ML interests
Generative AI, Natural Language Processing, Computer Vision
Recent Activity
View all activity
Papers
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
NearID: Identity Representation Learning via Near-identity Distractors
Update README.md
1
#2 opened 10 days ago
by 
Zaid
YimengChen
authored 6
papers 17 days ago
Self-Improvements in Modern Agentic Systems: A Survey
Paper • 2607.13104 • Published • 33
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
Paper • 2606.18829 • Published • 18
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Paper • 2606.16821 • Published • 4
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
Paper • 2606.12087 • Published • 79
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Paper • 2510.21614 • Published • 22
YimengChen
submitted a
paper to Daily Papers 18 days ago
DmitriiKhizbullin
updated a
dataset about 1 month ago
DmitriiKhizbullin
published a
dataset about 1 month ago
DmitriiKhizbullin
updated a
dataset about 1 month ago
DmitriiKhizbullin
published a
dataset about 1 month ago
babytreecc
authored a
paper 4 months ago
Aleksandar
submitted a
paper to Daily Papers 4 months ago
bing-li-ai
authored a
paper 5 months ago
bing-li-ai
submitted a
paper to Daily Papers 5 months ago
bing-li-ai
authored a
paper 5 months ago
SultanR
authored 3
papers 7 months ago
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures
Paper • 2510.24081 • Published • 24
Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets
Paper • 2512.18834 • Published • 4
SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data
Paper • 2511.18411 • Published • 1