activity
20162021
most citedStabilizing Training of Generative Adversarial Networks through Regularization

204 citations · 407 across the 11 of their papers we have counts for

collaborators
Showing 2019Show all

2 papers · 1 filter

cs.LG2019★ 20 cited

Adversarial Training is a Form of Data-dependent Operator Norm Regularization

Kevin Roth, Yannic Kilcher, Thomas Hofmann

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we prove that -norm constrained projec…

cs.LG2019

The Odds are Odd: A Statistical Test for Detecting Adversarial Examples

Kevin Roth, Yannic Kilcher, Thomas Hofmann

We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack. These statistics can…