Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Leitao, Mao, Qinghua, Liu, Daizong, Wang, Kun, Wang, Wenjie, Teng, Yan, Shao, Jing, Liu, Dongrui
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.21541