Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yiyang, Yu, Chaojian, Hong, Ziming, Shao, Yuanjie, Peng, Qinmu, Liu, Tongliang, You, Xinge
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.05809