Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

Published: 22 Jan 2025, Last Modified: 27 Feb 2025ICLR 2025 PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: computer vision, adversarial defense, adversarial robustness, robustness-accuracy trade-off
TL;DR: We identify novel key challenges in applying invariance regularization to adversarial training for improving the robustness-accuracy trade-off, and provide novel solutions.
Abstract: Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model invariance under adversarial perturbations; however, it still leads to accuracy loss. In this work, we closely analyze the challenges of using invariance regularization in adversarial training and understand how to address them. Our analysis identifies two key issues: (1) a "gradient conflict" between invariance and classification objectives, leading to suboptimal convergence, and (2) the mixture distribution problem arising from diverged distributions between clean and adversarial inputs. To address these issues, we propose Asymmetric Representation-regularized Adversarial Training (ARAT), which incorporates asymmetric invariance loss with stop-gradient operation and a predictor to avoid gradient conflict, and a split-BatchNorm (BN) structure to resolve the mixture distribution problem. Our detailed analysis demonstrates that each component effectively addresses the identified issues, offering novel insights into adversarial defense. ARAT shows superiority over existing methods across various settings. Finally, we discuss the implications of our findings to knowledge distillation-based defenses, providing a new perspective on their relative successes.
Supplementary Material: zip
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.
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: 7529
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview