TrustSafeAI

community

https://sites.google.com/site/pinyuchenpage/home

AI & ML interests

Research Demos and Tools for Trustworthy and Safe AI Development and Deployment

authored 3 papers 2 months ago

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

Paper • 2506.05346 • Published Jun 5, 2025

Spectral Insights into Data-Oblivious Critical Layers in Large Language Models

Paper • 2506.00382 • Published May 31, 2025

NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration

Paper • 2211.16274 • Published Nov 29, 2022

updated a Space 2 months ago

NCTV: Neural Clamping Toolkit and Visualization

Model-agnostic Toolkit for Neural Network Calibration

updated a Space 5 months ago

Test Time Calibration

Test-time calibration for improving test-time reasoning

published a Space 5 months ago

Test Time Calibration

Test-time calibration for improving test-time reasoning

updated a Space 5 months ago

LLM Physical Safety

LLM benchmark for Physical Safety

authored a paper 6 months ago

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

Paper • 2411.14133 • Published Nov 21, 2024 • 1

updated a Space 8 months ago

README

updated a collection 8 months ago

DivEye: Diversity-Driven AI Text Detector

https://openreview.net/forum?id=QuDDXJ47nq • 1 item • Updated Jul 15, 2025

updated a model 9 months ago

TrustSafeAI/AudioDeepfakeDetectors

Updated Jun 18, 2025

updated a Space 9 months ago

CoP Agentic Red-teaming

Generate jailbreak prompts for LLMs using principles

updated a Space 9 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

updated a Space 9 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

published a model 9 months ago

TrustSafeAI/AudioDeepfakeDetectors

Updated Jun 18, 2025

published a Space 9 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

updated a Space 10 months ago

CoP Agentic Red-teaming

Generate jailbreak prompts for LLMs using principles

updated 2 Spaces 10 months ago

README

AudioPerturber

Evaluate audio deepfake detection robustness under corruptions

published a Space 10 months ago

AudioPerturber

Evaluate audio deepfake detection robustness under corruptions