bsafe

non-profit

AI & ML interests

None defined yet.

Recent Activity

Yuetian authored a paper 15 days ago

BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views

kaiyuanzh authored a paper over 3 years ago

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

View all activity

authored a paper 15 days ago

BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views

Paper • 2610.17457 • Published 27 days ago • 3

authored a paper over 3 years ago

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

Paper • 2210.12873 • Published Feb 27, 2023