Distributed Adversarial Training to Robustify Deep Neural Networks at Scale

Gaoyuan Zhang, Songtao Lu, Yihua Zhang, Xiangyi Chen, Pin Yu Chen, Quanfu Fan, Lee Martie, Lior Horesh, Mingyi Hong, Sijia Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as adversarial training (AT), has been shown to mitigate the negative impact of adversarial attacks by virtue of a min-max robust training method. While effective, it remains unclear whether it can successfully be adapted to the distributed learning context. The power of distributed optimization over multiple machines enables us to scale up robust training over large models and datasets. Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines. We show that DAT is general, which supports training over labeled and unlabeled data, multiple types of attack generation methods, and gradient compression operations favored for distributed optimization. Theoretically, we provide, under standard conditions in the optimization theory, the convergence rate of DAT to the first-order stationary points in general non-convex settings. Empirically, we demonstrate that DAT either matches or outperforms state-of-the-art robust accuracies and achieves a graceful training speedup (e.g., on ResNet-50 under ImageNet). Codes are available at https://github.com/dat-2022/dat.

Original languageEnglish (US)
Title of host publicationProceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022
PublisherAssociation For Uncertainty in Artificial Intelligence (AUAI)
Pages2353-2363
Number of pages11
ISBN (Electronic)9781713863298
StatePublished - 2022
Event38th Conference on Uncertainty in Artificial Intelligence, UAI 2022 - Eindhoven, Netherlands
Duration: Aug 1 2022Aug 5 2022

Publication series

NameProceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022

Conference

Conference38th Conference on Uncertainty in Artificial Intelligence, UAI 2022
Country/TerritoryNetherlands
CityEindhoven
Period8/1/228/5/22

Bibliographical note

Funding Information:
Y. Zhang and S. Liu are supported by the Cisco Research grant CG# 70614511. P. Khanduri and M. Hong are supported in part by the NSF grants 1910385 and 1727757. We also thank Dr. Cho-Jui Hsieh for the helpful discussion on early ideas of this paper.

Publisher Copyright:
© 2022 Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022. All right reserved.

Fingerprint

Dive into the research topics of 'Distributed Adversarial Training to Robustify Deep Neural Networks at Scale'. Together they form a unique fingerprint.

Cite this