Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models
Published in arXiv preprint arXiv:2411.07559, 2024
Recommended citation: Tiejin Chen, Kaishen Wang, and Hua Wei. (2024). "Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models." arXiv preprint arXiv:2411.07559, 2024.
Download Paper