TrustSafeAI

community

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

pinyuchenTW

pinyuchen

Request to join this org

AI & ML interests

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

Collections 3

spaces 8

LLM Physical Safety

LLM benchmark for Physical Safety

NeuralFuse

Protect Model from Suffering Low-voltage-induced Bit Errors

Attention Tracker Prompt Injection Detector

Attention Tracker: Prompt Injection Detector

NCTV: Neural Clamping Toolkit and Visualization

Model-agnostic Toolkit for Neural Network Calibration

GREAT Score

GradientCuff-Jailbreak-Defense

Demonstration of Gradient Cuff: A Jailbreak Defense

models 1

TrustSafeAI/RADAR-Vicuna-7B

Text Classification • Updated Nov 7, 2023 • 80k • 6

datasets 1

TrustSafeAI/llm_physical_safety_benchmark

Viewer • Updated 17 days ago • 408 • 23