Skip to main navigation Skip to search Skip to main content

Proximal Splitting Adversarial Attack for Semantic Segmentation

  • École de technologie supérieure
  • Université Paris-Saclay

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

34 Citations (Scopus)

Abstract

Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately solve the adversarial segmentation problem and, therefore, overestimate the size of the perturbations required to fool models. Here, we propose a white-box attack for these models based on a proximal splitting to produce adversarial perturbations with much smaller ℓ∞ norms. Our attack can handle large numbers of constraints within a nonconvex minimization framework via an Augmented Lagrangian approach, coupled with adaptive constraint scaling and masking strategies. We demonstrate that our attack significantly outperforms previously proposed ones, as well as classification attacks that we adapted for segmentation, providing a first comprehensive benchmark for this dense task.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PublisherIEEE Computer Society
Pages20524-20533
Number of pages10
ISBN (Electronic)9798350301298
DOIs
Publication statusPublished - 2023
Event2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Duration: 17 Jun 2023 → 24 Jun 2023

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (Print)1063-6919

Conference

Conference2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Country/TerritoryCanada
CityVancouver
Period17/06/23 → 24/06/23

Keywords

  • Adversarial attack and defense

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Proximal Splitting Adversarial Attack for Semantic Segmentation'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this