Dual Intention Escape: Penetrating and Toxic Jailbreak Attack against Large Language Models.

@inproceedings{xue-2025-dual, author = {Yanni Xue and Jiakai Wang and Zixin Yin and Yuqing Ma and Haotong Qin and Renshuai Tao and Xianglong Liu}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Dual Intention Escape: Penetrating and Toxic Jailbreak Attack against Large Language Models}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {863--871}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714654}, doi = {https://doi.org/10.1145/3696410.3714654} }