Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhifang, He, Shuo, Wang, Haobo, Shen, Bingquan, Feng, Lei
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.20392