SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
Published in In Proceedings of NAACL 2025 (CCF-B, main conference)
Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen
Zeguan Xiao
Final-year PhD candidate @ SUFE SCAI. LLM Safety, Alignment, Robustness & Unlearning.
- Shanghai, China
- Google Scholar
- GitHub