Improving Adversarial Transferability on Vision Transformers via Dual-Flow Adversarial Attack

AI Summary1 min read

TL;DR

This paper introduces a dual-flow adversarial attack method to enhance transferability on Vision Transformers by addressing limitations of fixed-decay EMA in smoothing token embeddings.

Improving Adversarial Transferability on Vision Transformers via Dual-Flow Adversarial Attack

Bohai Zhou; Anlu Shi; Wei Wu
https://doi.org/10.1109/ACCESS.2025.3649234
Volume 14

State-of-the-art transferable adversarial attack methods for Vision Transformers (ViTs) have introduced token-embedding momentum inside the Transformer blocks, but they typically rely on fixed-decay exponential moving averages (EMA) to smooth historical embeddings. While EMA can suppress noise, it ignores the varying usefulness of historical information across time steps; moreover, cross-architect...

Visit Website