Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

TL;DR

This paper introduces DeCoWA, a deformation-constrained warping attack that enhances adversarial transferability across different model types, significantly improving attack success in diverse tasks.

Contribution

The paper proposes DeCoWA, a novel deformation-constrained warping method, to improve adversarial transferability across different model genera, addressing limitations of existing approaches.

Findings

DeCoWA significantly improves transferability between CNNs and Transformers.

The method is effective across multiple tasks including image, video, and audio recognition.

Extensive experiments validate the robustness of the proposed attack.

Abstract

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://github.com/LinQinLiang/DeCoWA.