Optical firewall for defending deep neural networks from adversarial attacks

Vladislav Kravets, Bahram Javidi, Adrian Stern

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

Abstract

We overview approaches that we have recently introduced that employ optical encrypted acquisition to defend against adversarial attacks on deep learning algorithms.

Original languageEnglish
Title of host publicationFrontiers in Optics, FiO 2021
PublisherOptica Publishing Group (formerly OSA)
ISBN (Electronic)9781557528209
DOIs
StatePublished - 1 Jan 2021
EventFrontiers in Optics + Laser Science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021 - Virtual, Online, United States
Duration: 1 Nov 20214 Nov 2021

Publication series

NameOptics InfoBase Conference Papers

Conference

ConferenceFrontiers in Optics + Laser Science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021
Country/TerritoryUnited States
CityVirtual, Online
Period1/11/214/11/21

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Mechanics of Materials

Fingerprint

Dive into the research topics of 'Optical firewall for defending deep neural networks from adversarial attacks'. Together they form a unique fingerprint.

Cite this