• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage StatisticsView Google Analytics Statistics

    Defending machine learning models against adversarial attacks using GANs

    Thumbnail
    View/Open
    Dissertation (5.600Mb)
    Date
    2019
    Author
    Malaviya, Shubham M.
    Metadata
    Show full item record
    Abstract
    We have used Generative Adversarial Network (GAN) to defend against adversarial attacks. Pixel-wise and perceptual distance measures for images are used in the GAN training. We have used five different distance measures, Reconstruction error, Structural SIMilarity (SSIM), Multi-Scale SSIM, Peak signal-to-noise ratio (PSNR), and Frechet Inception Distance (FID), in the GAN training. Although accuracies achieved against adversarial attacks with the proposed idea is not at par with the state of the art pproaches such as [38], the generator trained using FID is able to generate good quality images in lesser number of iterations. Using onlym a perceptual distance measure in the cost function does not guarantee the convergence of GAN training.
    URI
    http://drsr.daiict.ac.in//handle/123456789/862
    Collections
    • M Tech Dissertations [820]

    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     


    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV