Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Jinhu, Lou, Yihang, Si, Qingyi, Zhang, Shudong, Bai, Yan, Su, Sen
Format:	Preprint
Published:	2026
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/2603.27240