TrustSafeAI

community

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

pinyuchenTW

pinyuchen

AI & ML interests

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

kumitang

updated a Space 3 months ago

Test Time Calibration

Test-time calibration for improving test-time reasoning

kumitang

published a Space 3 months ago

Test Time Calibration

Test-time calibration for improving test-time reasoning

kumitang

updated a Space 3 months ago

LLM Physical Safety

LLM benchmark for Physical Safety

FloofCat

authored a paper 4 months ago

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

Paper • 2411.14133 • Published Nov 21, 2024 • 1

pinyuchen

updated a Space 6 months ago

README

pinyuchen

updated a collection 6 months ago

DivEye: Diversity-Driven AI Text Detector

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

xljesse

updated a model 7 months ago

TrustSafeAI/AudioDeepfakeDetectors

Updated Jun 18, 2025

bxiong

updated a Space 7 months ago

CoP Agentic Red-teaming

Generate jailbreak prompts for LLMs using principles

pinyuchen

updated a Space 7 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

xljesse

updated a Space 7 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

xljesse

published a model 7 months ago

TrustSafeAI/AudioDeepfakeDetectors

Updated Jun 18, 2025

xljesse

published a Space 7 months ago

AudioDeepfakeDetector

Detect fake audio using uploaded files

pinyuchen

updated a Space 7 months ago

CoP Agentic Red-teaming

Generate jailbreak prompts for LLMs using principles

xljesse

updated 2 Spaces 7 months ago

README

AudioPerturber

Evaluate audio deepfake detection robustness under corruptions

xljesse

published a Space 7 months ago

AudioPerturber

Evaluate audio deepfake detection robustness under corruptions

bxiong

published a Space 8 months ago

CoP Agentic Red-teaming

Generate jailbreak prompts for LLMs using principles

zaitang

updated a Space 10 months ago

Retention Score

Evaluate jailbreak risks for Vision-Language Models using Retention Score

gregH

updated a Space 10 months ago

Token Highlighter

Demonstration of Token Highlighter: A Jailbreak Defense

pinyuchen

authored a paper 10 months ago

Forecasting Open-Weight AI Model Growth on Hugging Face

Paper • 2502.15987 • Published Feb 21, 2025 • 10