Skip to main navigation Skip to search Skip to main content

Adversarial Attacks and Defenses in Computer Vision

  • Yu Ji
  • , Wenzhi Wu
  • , Hang Chen
  • , Zhengjun Liu*
  • *Corresponding author for this work
  • Heilongjiang University
  • Space Engineering University
  • School of Physics, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Computer vision systems have demonstrated excellent performance in tasks such as image classification, target detection, and face recognition. However, the deep neural networks that drive these systems are highly susceptible to interference from tiny, carefully designed perturbations, namely adversarial samples. These samples are virtually imperceptible to the human eye yet can lead to serious misjudgments in the model, revealing the fragility of its decision boundary and its fundamental difference from human perception. Conversely, defense strategies aim to improve robustness of models against adversarial attacks and ensure accurate outputs in the face of malicious attacks.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Science and Business Media Deutschland GmbH
Pages79-105
Number of pages27
DOIs
StatePublished - 2026
Externally publishedYes

Publication series

NameStudies in Computational Intelligence
Volume1246
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Keywords

  • Adversarial attacks
  • Computer vision
  • Decision boundary
  • Defenses strategy

Fingerprint

Dive into the research topics of 'Adversarial Attacks and Defenses in Computer Vision'. Together they form a unique fingerprint.

Cite this