• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    Robustness of Adversarial Attacks in Sound Event Classification 
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Robustness of Adversarial Attacks in Sound Event Classification
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Robustness of Adversarial Attacks in Sound Event Classification
    ‌
    ‌

    Browse

    All of QMROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    ‌
    ‌

    Administrators only

    Login
    ‌
    ‌

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Robustness of Adversarial Attacks in Sound Event Classification

    View/Open
    Accepted Version (310.6Kb)
    Pagination
    239 - 243
    Publisher URL
    http://dcase.community/workshop2019/
    Metadata
    Show full item record
    Abstract
    An adversarial attack is a method to generate perturbations to the input of a machine learning model in order to make the output of the model incorrect. The perturbed inputs are known as adversarial examples. In this paper, we investigate the robustness of adversarial examples to simple input transformations such as mp3 compression, resampling, white noise and reverb in the task of sound event classification. By performing this analysis, we aim to provide insights on strengths and weaknesses in current adversarial attack algorithms as well as provide a baseline for defenses against adversarial attacks. Our work shows that adversarial attacks are not robust to simple input transformations. White noise is the most consistent method to defend against adversarial attacks with a success rate of 73.72% averaged across all models and attack algorithms.
    Authors
    SUBRAMANIAN, V; Benetos, E; Sandler, M; 4th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2019)
    URI
    https://qmro.qmul.ac.uk/xmlui/handle/123456789/59658
    Collections
    • Electronic Engineering and Computer Science [2816]
    Copyright statements
    © The Author(s) 2019
    Twitter iconFollow QMUL on Twitter
    Twitter iconFollow QM Research
    Online on twitter
    Facebook iconLike us on Facebook
    • Site Map
    • Privacy and cookies
    • Disclaimer
    • Accessibility
    • Contacts
    • Intranet
    • Current students

    Modern Slavery Statement

    Queen Mary University of London
    Mile End Road
    London E1 4NS
    Tel: +44 (0)20 7882 5555

    © Queen Mary University of London.