Boosting adversarial transferability in vision-language models via multimodal feature heterogeneity

Abstract Vision-language pre-training models have achieved significant success in the field of medical imaging but have exhibited vulnerability to adversarial examples. Although adversarial attacks are harmful, they are valuable in revealing the weaknesses of VLP models and enhancing their robustnes...

Full description

Saved in:
Bibliographic Details
Main Authors: Long Chen, Yuling Chen, Zhi Ouyang, Hui Dou, Yangwen Zhang, Haiwei Sang
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-91802-6
Tags: Add Tag
No Tags, Be the first to tag this record!