Skip to content

spencerwooo/dSVA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

dSVA

arXiv ICCV 2025 Paper License

Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features

Shangbo Wu, Yu-an Tan, Ruinan Ma, Wencong Ma, Dehua Zhu, Yuanzhang Li^

Figure 1 (Optimized for GitHub)

TL;DR

We present dSVA, a generative dual self-supervised ViT features attack, that exploits dual self-supervised ViT features -- both from contrastive learning (e.g., DINO) and masked image modeling (e.g., MAE) -- to achieve remarkable black-box adversarial transferability, outperforming state-of-the-arts.

License

The source code is released under the MIT License.

N.B.: To appear in ICCV 2025. This repo will soon be updated, stay tuned.

About

Official implementation for "Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features" (ICCV 2025)

Resources

License

Stars

Watchers

Forks

Contributors