Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Shiji, Duan, Ranjie, Wang, Fengxiang, Chen, Chi, Kang, Caixin, Ruan, Shouwei, Tao, Jialing, Chen, YueFeng, Xue, Hui, Wei, Xingxing
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.04931