BackdoorLLM

AI & ML interests

Trustworthy ML/AI

Recent Activity

hanxunh  authored a paper 17 days ago

T2UE: Generating Unlearnable Examples from Text Descriptions

hanxunh  authored a paper 17 days ago

CURVALID: Geometrically-guided Adversarial Prompt Detection

hanxunh  authored a paper 4 months ago

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

View all activity

Team members 4