TrustSafeAI

AI & ML interests

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

Recent Activity

gregH  submitted a paper 30 days ago

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

gregH  authored a paper about 1 month ago

RADAR: Robust AI-Text Detection via Adversarial Learning

gregH  authored a paper about 1 month ago

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes

View all activity

Team members 12