A principled approach for generating adversarial images under non-smooth dissimilarity metrics

Published in Artificial Intelligence and Statistics (AISTATS), 2020

Recommended citation: Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel, and Adam M. Oberman. "A principled approach for generating adversarial images under non-smooth dissimilarity metrics." 23rd International Conference on Artificial Intelligence and Statistics (2020).

Download paper here