Adversarial Training from Mean Field Perspective

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 spotlightEveryoneRevisionsBibTeX
Keywords: adversarial training; mean field theory
TL;DR: We propose a new framework based on mean field theory and analyze adversarial training theoretically.
Abstract: Although adversarial training is known to be effective against adversarial examples, training dynamics are not well understood. In this study, we present the first theoretical analysis of adversarial training in random deep neural networks without any assumptions on data distributions. We introduce a new theoretical framework based on mean field theory, which addresses the limitations of existing mean field-based approaches. Based on the framework, we derive the (empirically tight) upper bounds of $\ell_q$ norm-based adversarial loss with $\ell_p$ norm-based adversarial examples for various values of $p$ and $q$. Moreover, we prove that networks without shortcuts are generally not adversarially trainable and that adversarial training reduces network capacity. We also show that the network width alleviates these issues. Furthermore, the various impacts of input and output dimensions on the upper bounds and time evolution of weight variance are presented.
Submission Number: 1078