Distract Large Language Models for Automatic Jailbreak Attack
Published in In Proceedings of EMNLP 2024 (CCF-B, main conference)
Zeguan Xiao, Yan Yang, Guanhua Chen, Yun Chen
Zeguan Xiao
Final-year PhD candidate @ SUFE SCAI. LLM Safety, Alignment, Robustness & Unlearning.
- Shanghai, China
- Google Scholar
- GitHub