BackdoorLLM

AI & ML interests

Trustworthy ML/AI

Recent Activity

hanxunh  authored a paper 5 days ago

Semantic-aware Adversarial Fine-tuning for CLIP

hanxunh  authored a paper 22 days ago

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models

hanxunh  authored a paper 22 days ago

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs

View all activity

Team members 4