Mutual-modality Adversarial Attack with Semantic Perturbation

TL;DR

This paper introduces a mutual-modality adversarial attack method leveraging CLIP, which enhances attack transferability across models by iteratively optimizing visual perturbations and textual defenses, outperforming existing methods.

Contribution

The paper proposes a novel mutual-modality optimization scheme for adversarial attacks using CLIP, improving transferability and stability across different models.

Findings

Effective high-transferable attacks demonstrated on benchmark datasets.

Outperforms state-of-the-art attack methods.

Stable attack performance regardless of target networks.

Abstract

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are frequently treated as a black box, consequently mitigating the vulnerability to such attacks. Thus, enhancing the transferability of the adversarial samples has become a crucial area of research, which heavily relies on selecting appropriate surrogate models. To address this challenge, we propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach is accomplished by leveraging the pre-trained CLIP model. Firstly, we conduct a visual attack on the clean image that causes semantic perturbations on the aligned embedding space with the other textual modality. Then, we apply the corresponding defense on the textual modality by updating the prompts, which forces the re-matching on the perturbed embedding space. Finally, to enhance the attack transferability, we utilize the iterative training strategy on the visual attack and the textual defense, where the two processes optimize from each other. We evaluate our approach on several benchmark datasets and demonstrate that our mutual-modal attack strategy can effectively produce high-transferable attacks, which are stable regardless of the target networks. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.