98 citations · 105 across the 3 of their papers we have counts for
4 papers
PopSkipJump: Decision-Based Attack for Probabilistic Classifiers
Carl-Johann Simon-Gabriel, Noman Ahmed Sheikh, Andreas Krause
Most current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output. Many existing attack algorithms cover various sett…
First-order Adversarial Vulnerability of Neural Networks and Input Dimension
Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou +2
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We…
From optimal transport to generative modeling: the VEGAN cookbook
Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin +2
We study unsupervised generative modeling in terms of the optimal transport (OT) problem between true (but unknown) data distribution and the latent variable model distributi…
Removing systematic errors for exoplanet search via latent causes
Bernhard Schölkopf, David W. Hogg, Dun Wang +4
We describe a method for removing the effect of confounders in order to reconstruct a latent quantity of interest. The method, referred to as half-sibling regression, is inspired b…