Combating Adversaries with Anti-adversaries

Motasem Alfarra, Juan C. Pérez, Ali Thabet, Adel Bibi, Philip H.S. Torr, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. In particular, our layer generates an input perturbation in the opposite direction of the adversarial one and feeds the classifier a perturbed version of the input. Our approach is training-free and theoretically supported. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models and conduct large-scale experiments from black-box to adaptive attacks on CIFAR10, CIFAR100, and ImageNet. Our layer significantly enhances model robustness while coming at no cost on clean accuracy.

Original languageEnglish (US)
Title of host publicationAAAI-22 Technical Tracks 6
PublisherAssociation for the Advancement of Artificial Intelligence
Pages5992-6000
Number of pages9
ISBN (Electronic)1577358767, 9781577358763
StatePublished - Jun 30 2022
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: Feb 22 2022Mar 1 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume36

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period02/22/2203/1/22

Bibliographical note

Funding Information:
This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSR-CRG2019-4033. We would also like to thank Humam Alwassel for the help and discussion.

Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Combating Adversaries with Anti-adversaries'. Together they form a unique fingerprint.

Cite this