@inproceedings{li-etal-2025-cavgan, title = "{CAVGAN}: Unifying Jailbreak and Defense of {LLM}s via Generative Adversarial Attacks on their Internal Representations", author = "Li, Xiaohu and Ning, Yunfeng and Bao, Zepeng and Xu, Mayi and Chen, Jianhao and Qian, Tieyun", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.346/", pages = "6664--6678", ISBN = "979-8-89176-256-5" }