Boosting the Targeted Transferability of Adversarial Examples via Salient Region & Weighted Feature Drop

TL;DR

This paper proposes SWFD, a novel framework that enhances the targeted transferability of adversarial examples by using salient regions and weighted feature drop, significantly improving attack success rates across models.

Contribution

The introduction of Salient region & Weighted Feature Drop (SWFD) method that addresses overfitting and improves transferability of adversarial examples in black-box attacks.

Findings

SWFD increases attack success rate by 16.31% on normally trained models.

SWFD improves success rate by 7.06% on robust models.

The method outperforms state-of-the-art approaches in diverse configurations.

Abstract

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial examples, which are generated from a substitute model and leveraged to attack unknown black-box models. Despite various proposals aimed at improving transferability, the success of these attacks in targeted black-box scenarios is often hindered by the tendency for adversarial examples to overfit to the surrogate models. In this paper, we introduce a novel framework based on Salient region & Weighted Feature Drop (SWFD) designed to enhance the targeted transferability of adversarial examples. Drawing from the observation that examples with higher transferability exhibit smoother distributions in the deep-layer outputs, we propose the weighted feature drop mechanism to modulate activation values according to weights scaled by norm distribution, effectively addressing the overfitting issue when generating adversarial examples. Additionally, by leveraging salient region within the image to construct auxiliary images, our method enables the adversarial example's features to be transferred to the target category in a model-agnostic manner, thereby enhancing the transferability. Comprehensive experiments confirm that our approach outperforms state-of-the-art methods across diverse configurations. On average, the proposed SWFD raises the attack success rate for normally trained models and robust models by 16.31% and 7.06% respectively.