DBA: Downsampling-Based Adversarial Attack in Medical Image Analysis

Zhaoxuan Wang, Shiyu Zhang, Yang Li, Quan Pan

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

1 Scopus citations

Abstract

The next-generation of artificial intelligence technology has contributed significantly to the development of medical intelligence. However, the widespread use of deep neural networks (DNNs) has also brought about serious security threats. In this paper, we present an adversarial attack approach for deep learning-based image segmentation models in the field of medical image analysis. In our solutions, we propose a novel adversarial attack method, which is designed to exploit the DNNs’ generic down-sampling operation to ensure the effectiveness, stealthiness, and transferability of the attack. We perform the attack on two State-Of-The-Art (SOTA) models, DDANet and CaraNet in a general medical image dataset Kvasir-SEG, and a comprehensive evaluation shows that our attack is effective stealthy, and transferrable.

Original languageEnglish
Title of host publicationThird International Conference on Computer Vision and Pattern Analysis, ICCPA 2023
EditorsLinlin Shen, Guoqiang Zhong
PublisherSPIE
ISBN (Electronic)9781510667563
DOIs
StatePublished - 2023
Event3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023 - Hangzhou, China
Duration: 7 Apr 20239 Apr 2023

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12754
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023
Country/TerritoryChina
CityHangzhou
Period7/04/239/04/23

Keywords

  • Adversarial Attack
  • Deep Neural Networks
  • Medical Image Segmentation

Fingerprint

Dive into the research topics of 'DBA: Downsampling-Based Adversarial Attack in Medical Image Analysis'. Together they form a unique fingerprint.

Cite this