Gradient Flow Provably Learns Robust Classifiers for Data from Orthonormal Clusters

Hancheng Min, Rene Vidal

Keywords: Orthonormal Clusters, Robust classifier, Two-layer Network, Gradient Flow

Abstract:

Deep learning-based classifiers are known to be vulnerable to adversarial attacks. Existing methods for defending against such attacks require adding a defense mechanism or modifying the learning procedure (e.g., by adding adversarial examples). This paper shows that for certain data distribution one can learn a provably robust classifier using standard learning methods and without adding a defense mechanism. More specifically, this paper addresses the problem of finding a robust classifier for a binary classification problem in which the data comes from a mixture of Gaussian clusters with orthonormal cluster centers. First, we characterize the largest $\ell_2$-attack any classifier can defend against while maintaining high accuracy, and show the existence of optimal robust classifiers achieving this maximum $\ell_2$-robustness. Next, we show that given data sampled from the orthonormal cluster model, gradient flow on a two-layer network with a polynomial ReLU activation and without adversarial examples provably finds an optimal robust classifier.

Primary Area: learning theory

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: 4030