Why adversarial training can hurt robust accuracy

Jacob Clarysse, Julia Hörrmann, Fanny Yang

Keywords: Adversarial training, Learning Theory, Robust generalisation

TL;DR: Adversarial training can hurt robust generalization for perceptible perturbations when the sample size is small

Abstract: Machine learning classifiers with high test accuracy often perform poorly under adversarial attacks. It is commonly believed that adversarial training alleviates this issue. In this paper, we demonstrate that, surprisingly, the opposite can be true for a natural class of perceptible perturbations --- even though adversarial training helps when enough data is available, it may in fact hurt robust generalization in the small sample size regime. We first prove this phenomenon for a high-dimensional linear classification setting with noiseless observations. Using intuitive insights from the proof, we could surprisingly find perturbations on standard image datasets for which this behavior persists. Specifically, it occurs for perceptible attacks that effectively reduce class information such as object occlusions or corruptions.

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: Theory (eg, control theory, learning theory, algorithmic game theory)