CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xiaohu, Ning, Yunfeng, Bao, Zepeng, Xu, Mayi, Chen, Jianhao, Qian, Tieyun
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.06043