Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zuoou, Zhang, Weitong, Wang, Jingyuan, Zhang, Shuyuan, Bai, Wenjia, Kainz, Bernhard, Qiao, Mengyun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.09218