Jailbreaking LLMs Through Alignment Vulnerabilities in Out-of-Distribution Settings.

@inproceedings{huang-2025-jailbreaking, author = {Yue Huang and Jingyu Tang and Dongping Chen and Bingda Tang and Yao Wan and Lichao Sun and Philip S. Yu and Xiangliang Zhang}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{Jailbreaking LLMs Through Alignment Vulnerabilities in Out-of-Distribution Settings}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {4817--4821}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3760899}, doi = {https://doi.org/10.1145/3746252.3760899} }