TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
arXiv:2603.03081v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft …
Zhi Xu, Jiaqi Li, Xiaotong Zhang, Hong Yu, Han Liu
조회수 27회