Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Hee-Seon, Kim, Minbeom, Kim, Changick
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.08108