Browsing 39-Issue 5 by Subject "Adversarial learning"

Now showing items 1-1 of 1

    • Generating Adversarial Surfaces via Band-Limited Perturbations 

      Mariani, Giorgio; Cosmo, Luca; Bronstein, Alex M.; Rodolà, Emanuele (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Adversarial attacks have demonstrated remarkable efficacy in altering the output of a learning model by applying a minimal perturbation to the input data. While increasing attention has been placed on the image domain, ...