One-Pixel Attack: Understanding and Improving Deep Neural Networks with Evolutionary Computation

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Recently, the one-pixel attack showed that deep neural networks (DNNs) can misclassify by changing only one pixel. Beyond a vulnerability, by demonstrating how easy it is to cause a change in classes, it revealed that DNNs are not learning the expected high-level features but rather less robust ones. In this chapter, recent findings further confirming the affirmations above will be presented together with an overview of current attacks and defenses. Moreover, it will be shown the promises of evolutionary computation as both a way to investigate the robustness of DNNs as well as a way to improve their robustness through hybrid systems, evolution of architectures, among others.

Original languageEnglish
Title of host publicationNatural Computing Series
PublisherSpringer
Pages401-430
Number of pages30
DOIs
Publication statusPublished - Jan 1 2020

Publication series

NameNatural Computing Series
ISSN (Print)1619-7127

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'One-Pixel Attack: Understanding and Improving Deep Neural Networks with Evolutionary Computation'. Together they form a unique fingerprint.

  • Cite this