Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Jianhao, Chen, Haoyang, Zhao, Hanjie, Liang, Haozhe, Qian, Tieyun
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.12616