Optical firewall for defending deep neural networks from adversarial attacks

Vladislav Kravets, Bahram Javidi, Adrian Stern

    Research output: Contribution to journalConference articlepeer-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 languageAmerican English
    Article numberFW5A.2
    JournalOptics InfoBase Conference Papers
    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

    All Science Journal Classification (ASJC) codes

    • 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