Imperceptible adversarial attack with entropy feature and segmentation-based constraint

Rongdong Li, Qinliang Lin, Yinglong Fu, Weicheng Xie, Linlin Shen

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

Abstract

Methods of adversarial attack and defense have attracting increasing attention in the fields of security and protection related applications. However, current algorithms carry out perturbations on entire images and mostly consider their imperceptibility to machines, while does not take their human imperceptibility into account. In this work, we propose a constrained adversarial attack algorithm with both machine and human imperceptibility based on image entropy feature and accurate segmentation. The proposed algorithm has three merits. First, image entropy-based feature for quantifying the imperceptibility of a semantic region is introduced, which is simple yet efficient to implement. Second, in terms of the imperceptibility metric, accurate target regions for adversarial perturbation are obtained based on scene-aware segmentation and merging. Third, a general adversarial attack based on segmentation region constraint is proposed to induce both machine and visual imperceptibility. Experimental results in terms of qualitative and quantitative analysis reflect the effectiveness of the proposed algorithm compared with the state of the arts.

Original languageEnglish
Title of host publicationICCPR 2021 - Proceedings of 2021 10th International Conference on Computing and Pattern Recognition
PublisherAssociation for Computing Machinery
Pages12-17
Number of pages6
ISBN (Electronic)9781450390439
DOIs
Publication statusPublished - 15 Oct 2021
Externally publishedYes
Event10th International Conference on Computing and Pattern Recognition, ICCPR 2021 - Virtual, Online, China
Duration: 15 Oct 202117 Oct 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference10th International Conference on Computing and Pattern Recognition, ICCPR 2021
Country/TerritoryChina
CityVirtual, Online
Period15/10/2117/10/21

Keywords

  • Adversarial attack
  • constrained attack algorithm
  • imperceptibility metric
  • robust object classification
  • semantic segmentation

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Imperceptible adversarial attack with entropy feature and segmentation-based constraint'. Together they form a unique fingerprint.

Cite this