An ADMM-based universal framework for adversarial attacks on deep neural networks

Pu Zhao, Yanzhi Wang, Sijia Liu, Xue Lin

Research output: Chapter in Book/Entry/PoemConference contribution

20 Scopus citations

Abstract

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. In a successful adversarial attack, the targeted mis-classification should be achieved with the minimal distortion added. In the literature, the added distortions are usually measured by L 0 , L 1 , L 2 , and L norms, namely, L 0 , L 1 , L 2 , and L attacks, respectively. However, there lacks a versatile framework for all types of adversarial attacks. This work for the first time unifies the methods of generating adversarial examples by leveraging ADMM (Alternating Direction Method of Multipliers), an operator splitting optimization approach, such that L 0 , L 1 , L 2 , and L attacks can be effectively implemented by this general framework with little modifications. Comparing with the state-of-the-art attacks in each category, our ADMM-based attacks are so far the strongest, achieving both the 100% attack success rate and the minimal distortion.

Original languageEnglish (US)
Title of host publicationMM 2018 - Proceedings of the 2018 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Pages1065-1073
Number of pages9
ISBN (Electronic)9781450356657
DOIs
StatePublished - Oct 15 2018
Event26th ACM Multimedia conference, MM 2018 - Seoul, Korea, Republic of
Duration: Oct 22 2018Oct 26 2018

Publication series

NameMM 2018 - Proceedings of the 2018 ACM Multimedia Conference

Conference

Conference26th ACM Multimedia conference, MM 2018
Country/TerritoryKorea, Republic of
CitySeoul
Period10/22/1810/26/18

Keywords

  • ADMM (Alternating Direction Method of Multipliers)
  • Adversarial attacks
  • Deep neural networks

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'An ADMM-based universal framework for adversarial attacks on deep neural networks'. Together they form a unique fingerprint.

Cite this