Adversarial Masked Autoencoder Purifier with Defense Transferability

Yuan-Chih Chen, Chun-Shien Lu

Keywords: Adversarial attack, Adversarial defense, Purifier, Robustness, Security, Transferability

TL;DR: We are first to propose Masked AutoEncoder Purifier (MAEP), which integrates Masked AutoEncoder (MAE) into an adversarial purifier framework for test-time purification, and achieve SOTA robustness.

Abstract:

The study of adversarial defense still struggles to combat with advanced adversarial attacks.
In contrast to most prior studies that rely on the diffusion model for test-time defense to remarkably increase the inference time, we propose Masked AutoEncoder Purifier (MAEP), which integrates Masked AutoEncoder (MAE) into an adversarial purifier
framework for test-time purification.
While MAEP achieves promising adversarial robustness, it particularly features model defense transferability without relying on using additional data that is different from the training dataset.
To our knowledge, MAEP is the first study of adversarial purifier based on masked autoencoder.
Extensive experiments validate the proposed method.
Notably, MAEP trained on CIFAR10 achieves state-of-the-art performance even when tested directly on ImageNet, outperforming existing diffusion-based models trained specifically on ImageNet.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 8350