Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
This work addresses the problem of improving transferable adversarial attacks for security testing in vision systems, representing an incremental advance by applying prompt learning to generative attacks.
The paper tackles the challenge of creating adversarial examples that transfer across unknown domains and model architectures by proposing PDCL-Attack, a method that uses CLIP and prompt-driven feature guidance to enhance transferability, achieving superior performance over state-of-the-art methods in cross-domain and cross-model settings.
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.