arxiv:2402.03299
Haohan Wang
haohanw
ยท
AI & ML interests
trustworthy ML, computational biology
Recent Activity
authored
a paper
6 months ago
Robust Prompt Optimization for Defending Language Models Against
Jailbreaking Attacks
authored
a paper
6 months ago
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test
Guideline Adherence of Large Language Models
Organizations
