BackdoorLLM

AI & ML interests

Trustworthy ML/AI

Recent Activity

hanxunh  authored a paper 2 days ago

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

hanxunh  authored a paper 2 days ago

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs

hanxunh  authored a paper about 2 months ago

Internal Safety Collapse in Frontier Large Language Models

View all activity

Team members 4