AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs.
Jiawei Chen, Xiao Yang, Zhengwei Fang, Yu Tian, Yinpeng Dong, Zhaoxia Yin, Hang Su
Browse the full NAACL paper archive.
Jiawei Chen, Xiao Yang, Zhengwei Fang, Yu Tian, Yinpeng Dong, Zhaoxia Yin, Hang Su
Browse the full NAACL paper archive.