Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

arXiv2002.11798MaRDI QIDQ6335661

Author name not available (Why is that?)

Publication date: 26 February 2020

Abstract: Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability that captures the maximum change of mutual information between the input and output distributions, under the worst-case input perturbation. Then, we prove a theorem that establishes a lower bound on the minimum adversarial risk that can be achieved for any downstream classifier based on its representation vulnerability. We propose an unsupervised learning method for obtaining intrinsically robust representations by maximizing the worst-case mutual information between the input and output distributions. Experiments on downstream classification tasks support the robustness of the representations found using unsupervised learning with our training principle.

Has companion code repository: https://github.com/schzhu/learning-adversarially-robust-representations

This page was built for publication: Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6335661)