• Find People
  • Campus Map
  • PiratePort
  • A-Z
    • About
    • Submit
    • Browse
    • Login
    View Item 
    •   ScholarShip Home
    • Dissertations and Theses
    • Master's Theses
    • View Item
    •   ScholarShip Home
    • Dissertations and Theses
    • Master's Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of The ScholarShipCommunities & CollectionsDateAuthorsTitlesSubjectsTypeDate SubmittedThis CollectionDateAuthorsTitlesSubjectsTypeDate Submitted

    My Account

    Login

    Statistics

    View Google Analytics Statistics

    DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES

    Thumbnail
    View/ Open
    THOMAS-MASTERSTHESIS-2019.pdf (792.7Kb)

    Show full item record
    Author
    Thomas, Sam
    Abstract
    Adversarial machine learning has been an important area of study for the securing of machine learning systems. However, for every defense that is made to protect these artificial learners, a more sophisticated attack emerges to defeat it. This has created an arms race, with the problem of adversarial attacks never being fully mitigated. This thesis examines the field of adversarial machine learning; specifically, the property of transferability, and the use of dynamic defenses as a solution to attacks which leverage it. We show that this is an emerging field of research, which may be the solution to one of the most intractable problems in adversarial machine learning. We go on to implement a minimal experiment, demonstrating that research within this area is easily accessible. Finally, we address some of the hurdles to overcome in order to unify the disparate aspects of current related research.
    URI
    http://hdl.handle.net/10342/7284
    Subject
     adversarial machine learning; transferability 
    Date
    2019-05-02
    Citation:
    APA:
    Thomas, Sam. (May 2019). DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES (Master's Thesis, East Carolina University). Retrieved from the Scholarship. (http://hdl.handle.net/10342/7284.)

    Display/Hide MLA, Chicago and APA citation formats.

    MLA:
    Thomas, Sam. DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES. Master's Thesis. East Carolina University, May 2019. The Scholarship. http://hdl.handle.net/10342/7284. September 21, 2023.
    Chicago:
    Thomas, Sam, “DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES” (Master's Thesis., East Carolina University, May 2019).
    AMA:
    Thomas, Sam. DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES [Master's Thesis]. Greenville, NC: East Carolina University; May 2019.
    Collections
    • Computer Science
    • Master's Theses
    Publisher
    East Carolina University

    xmlui.ArtifactBrowser.ItemViewer.elsevier_entitlement

    East Carolina University has created ScholarShip, a digital archive for the scholarly output of the ECU community.

    • About
    • Contact Us
    • Send Feedback