AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models

Dong Shu, Mingyu Jin, Chong Zhang, Lingyao Li, Zihao Zhou, Yongfeng Zhang

Research output: Chapter in Book or Report/Conference proceeding › Chapter

20 Downloads (Pure)

Fingerprint

Dive into the research topics of 'AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models'. Together they form a unique fingerprint.

Computer Science