@article{stealthyjailbreakattacksonlargelanguage, title = {Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring}, author = {Honglin Mu and Han He and Yuxin Zhou and Yunlong Feng and Yang Xu and Libo Qin and Xiaoming Shi and Zeming Liu and Xudong Han and Qi Shi and Qingfu Zhu and Wanxiang Che}, year = {2024}, eprint = {2410.21083}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.21083v1}, }