Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

TL;DR

This paper introduces PDCL-Attack, a novel prompt-driven generative adversarial attack leveraging CLIP's semantic understanding to improve transferability across diverse vision models and domains.

Contribution

It is the first to incorporate prompt learning into generative adversarial attacks for enhanced transferability across models and domains.

Findings

Outperforms state-of-the-art transfer attack methods.

Effective across various cross-domain and cross-model scenarios.

Leverages semantic prompts from class labels for attack guidance.

Abstract

Recent vision-language foundation models, such as CLIP, have demonstrated superior capabilities in learning representations that can be transferable across diverse range of downstream tasks and domains. With the emergence of such powerful models, it has become crucial to effectively leverage their capabilities in tackling challenging vision tasks. On the other hand, only a few works have focused on devising adversarial examples that transfer well to both unknown domains and model architectures. In this paper, we propose a novel transfer attack method called PDCL-Attack, which leverages the CLIP model to enhance the transferability of adversarial perturbations generated by a generative model-based attack framework. Specifically, we formulate an effective prompt-driven feature guidance by harnessing the semantic representation power of text, particularly from the ground-truth class labels of input images. To the best of our knowledge, we are the first to introduce prompt learning to enhance the transferable generative attacks. Extensive experiments conducted across various cross-domain and cross-model settings empirically validate our approach, demonstrating its superiority over state-of-the-art methods.