COMBATING FALSE SENSE OF SECURITY: BREAKING THE DEFENSE OF ADVERSARIAL TRAINING VIA NON-GRADIENT ADVERSARIAL ATTACK

Mingyuan Fan, Yang Liu, Cen Chen, Shengxing Yu, Wenzhong Guo, Ximeng Liu

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

5 Scopus citations

Abstract

Adversarial training is believed to be the most robust and effective defense method against adversarial attacks. Gradient-based adversarial attack methods are generally adopted to evaluate the effectiveness of adversarial training. However, in this paper, by diving into the existing adversarial attack literature, we find that adversarial examples generated by these attack methods tend to be less imperceptible, which may lead to an inaccurate estimation for the effectiveness of the adversarial training. The existing adversarial attacks mostly adopt gradient-based optimization methods and such optimization methods have difficulties in searching the most effective adversarial examples (i.e., the global extreme points). On the contrast, in this work, we propose a novel Non-Gradient Attack (NGA) to overcome the above-mentioned problem. Extensive experiments show that NGA significantly outperforms the state-of-the-art adversarial attacks on Attack Success Rate (ASR) by 2% ∼ 7%.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3293-3297
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore
Duration: 22 May 202227 May 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityHybrid
Period22/05/2227/05/22

Keywords

  • adversarial attack
  • adversarial training
  • non-gradient attack

Fingerprint

Dive into the research topics of 'COMBATING FALSE SENSE OF SECURITY: BREAKING THE DEFENSE OF ADVERSARIAL TRAINING VIA NON-GRADIENT ADVERSARIAL ATTACK'. Together they form a unique fingerprint.

Cite this