Interpolated Adversarial Training: Achieving robust neural networks without sacrificing too much accuracy

Alex Lamb, Vikas Verma, Kenji Kawaguchi, Alexander Matyasko, Savya Khosla, Juho Kannala, Yoshua Bengio

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)
131 Downloads (Pure)

Abstract

Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how the adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve accuracy on the unperturbed data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial training. On CIFAR-10, adversarial training increases the standard test error ( when there is no adversary) from 4.43% to 12.32%, whereas with our Interpolated adversarial training we retain the adversarial robustness while achieving a standard test error of only 6.45%. With our technique, the relative increase in the standard error for the robust model is reduced from 178.1% to just 45.5%. Moreover, we provide mathematical analysis of Interpolated Adversarial Training to confirm its efficiencies and demonstrate its advantages in terms of robustness and generalization. (C) 2022 The Authors. Published by Elsevier Ltd.

Original languageEnglish
Pages (from-to)218-233
Number of pages16
JournalNeural Networks
Volume154
DOIs
Publication statusPublished - Oct 2022
MoE publication typeA1 Journal article-refereed

Keywords

  • Adversarial robustness
  • Mixup
  • Manifold Mixup
  • Standard test error

Fingerprint

Dive into the research topics of 'Interpolated Adversarial Training: Achieving robust neural networks without sacrificing too much accuracy'. Together they form a unique fingerprint.

Cite this