Enhancing the Transferability via Feature-Momentum Adversarial Attack

TL;DR

This paper introduces Feature-Momentum Adversarial Attack (FMAA), a novel method that dynamically updates guidance maps during attack iterations to improve transferability of adversarial examples across models.

Contribution

The paper proposes a dynamic guidance map approach using momentum to enhance transferability in feature-level adversarial attacks, outperforming existing methods.

Findings

FMAA significantly outperforms state-of-the-art methods in transferability.

Dynamic guidance maps better reflect network behavior during attack iterations.

Extensive experiments validate the effectiveness of FMAA across different models.

Abstract

Transferable adversarial attack has drawn increasing attention due to their practical threaten to real-world applications. In particular, the feature-level adversarial attack is one recent branch that can enhance the transferability via disturbing the intermediate features. The existing methods usually create a guidance map for features, where the value indicates the importance of the corresponding feature element and then employs an iterative algorithm to disrupt the features accordingly. However, the guidance map is fixed in existing methods, which can not consistently reflect the behavior of networks as the image is changed during iteration. In this paper, we describe a new method called Feature-Momentum Adversarial Attack (FMAA) to further improve transferability. The key idea of our method is that we estimate a guidance map dynamically at each iteration using momentum to effectively disturb the category-relevant features. Extensive experiments demonstrate that our method significantly outperforms other state-of-the-art methods by a large margin on different target models.