Understanding and Mitigating Robust Overfitting through the Lens of Feature Dynamics

Yifei Wang, Liangchen Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Keywords: Adversarial Training, Robust Overfitting, Generalization, Robustness, Adversarial Attack

Abstract: Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting robust features. However, researchers recently notice that AT suffers from severe robust overfitting problems, particularly after the learning rate (LR) decay, while the existing static view of feature robustness fails to explain this phenomenon. In this paper, we propose a new dynamic feature robustness framework which takes the dynamic interplay between the model trainer and the attacker into consideration. By tracing temporal and dataset-specific feature robustness, we develop a new understanding of robust overfitting from the dynamics of non-robust features, and empirically verify it on real-world datasets. Built upon this understanding, we explore three techniques to restore the balance between the model trainer and the attacker, and show that they could effectively alleviate robust overfitting and attain state-of-the-art robustness on benchmark datasets. Notably, different from previous studies, our interpretation highlights the necessity of considering the min-max nature of AT for robust overfitting.

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.

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: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)