Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack

Ruize Gao, Jiongxiao Wang, Kaiwen Zhou, Feng Liu, Binghui Xie, Gang Niu, Bo Han*, James Cheng*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

4 Citations (Scopus)

Abstract

The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available. However, the high computational cost (e.g., 100 times more than that of the project gradient descent attack) makes AA infeasible for practitioners with limited computational resources, and also hinders applications of AA in the adversarial training (AT). In this paper, we propose a novel method, minimum-margin (MM) attack, to fast and reliably evaluate adversarial robustness. Compared with AA, our method achieves comparable performance but only costs 3% of the computational time in extensive experiments. The reliability of our method lies in that we evaluate the quality of adversarial examples using the margin between two targets that can precisely identify the most adversarial example. The computational efficiency of our method lies in an effective Sequential TArget Ranking Selection (STARS) method, ensuring that the cost of the MM attack is independent of the number of classes. The MM attack opens a new way for evaluating adversarial robustness and provides a feasible and reliable way to generate high-quality adversarial examples in AT.
Original languageEnglish
Title of host publicationProceedings of 39th International Conference on Machine Learning (ICML 2022)
EditorsKamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, Sivan Sabato
PublisherML Research Press
Pages7144-7163
Number of pages20
Publication statusPublished - 17 Jul 2022
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore Convention Center , Baltimore, Maryland, United States
Duration: 17 Jul 202223 Jul 2022
https://icml.cc/Conferences/2022

Publication series

NameProceedings of Machine Learning Research
Volume162
ISSN (Print)2640-3498

Conference

Conference39th International Conference on Machine Learning, ICML 2022
Country/TerritoryUnited States
CityBaltimore, Maryland
Period17/07/2223/07/22
Internet address

Fingerprint

Dive into the research topics of 'Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack'. Together they form a unique fingerprint.

Cite this