Learning to Transform Dynamically for Better Adversarial Transferability

Rongyi Zhu, Zeliang Zhang, Zhuo Liu, Chenliang Xu, Susan Liang

Abstract: Adversarial examples, crafted by adding perturbations imperceptible to humans, can deceive neural networks. Re-cent studies identify the adversarial transferability across various models, i.e., the cross-model attack ability of adversarial samples. To enhance such adversarial transferability, existing input transformation-based methods diversify input data with transformation augmentation. However, their effectiveness is limited by the finite number of available transformations. In our study, we introduce a novel approach named Learning to Transform (L2T). L2T increases the diversity of transformed images by selecting the optimal combination of operations from a pool of candidates, consequently im-proving adversarial transferability. We conceptualize the selection of optimal transformation combinations as a tra-jectory optimization problem and employ a reinforcement learning strategy to effectively solve the problem. Comprehensive experiments on the ImageNet dataset, as well as practical tests with Google Vision and GPT-4V, reveal that L2T surpasses current methodologies in enhancing adversarial transferability, thereby confirming its effectiveness and practical significance. The code is available at https://github.com/ZhangAIPI/TransferAttack.