HSF: Defending against Jailbreak Attacks with Hidden State Filtering.

@inproceedings{qian-2025-hsf, author = {Cheng Qian and Hainan Zhang and Lei Sha and Zhiming Zheng}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{HSF: Defending against Jailbreak Attacks with Hidden State Filtering}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {2078--2087}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3717659}, doi = {https://doi.org/10.1145/3701716.3717659} }