APD: Boosting Adversarial Transferability via Perturbation Dropout

ZongQi Wang, Wenchao Xu, Haozhao Wang, Nan Cheng

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: adversarial example, trustworthy AI

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: The transferability of adversarial attack to deep neural networks (DNNs) accounts for the possibility that the adversarial examples crafted for a known model can also mislead other unseen models in black-box setting. Existing literature to improve the adversarial transferability often focus on spreading the adversarial perturbations towards the whole image, which can be counter-productive as the extended perturbation can hardly track the attention regions across different models. That's because although they spread the perturbation throughout the entire image but they do not consider the mutual influence of different perturbation regions. In this paper, we propose a simple yet effective perturbation-dropping scheme that can enhance the transferability of the adversarial examples by incorporating the dropout mechanism during their optimization process. Specifically, we leverage the class activation map (CAM) to locate the midpoint of the dropped regions, whereby the effective perturbation can be generated for the target models while maintaining the attack rate towards the source model even if some blocks of the perturbation noises are dropped. Extensive experiments are conducted on the ImageNet dataset, which demonstrates that the proposed method outperforms state-of-the-art methods, that achieve both high attack efficiency and transferability.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 785