Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks

2 code implementations • 30 Sep 2018 • Kenneth T. Co, Luis Muñoz-González, Sixte de Maupeou, Emil C. Lupu

Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time.

Bayesian Optimization