Browsing Volume 39 (2020) by Subject "Adversarial learning"
Now showing items 1-1 of 1
-
Generating Adversarial Surfaces via Band-Limited Perturbations
(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, ...