Training Adversarially Robust Sparse Networks via Bayesian
Connectivity Sampling
Ozan Ozdenizci 1 2 Robert Legenstein 1
Abstract Seminal work by (Szegedy et al., 2013) showed that such
adversarial examples can be created via perturbations that
Deep neural networks have been shown to be
are hardly perceptible to humans, which exposed important
susce ...


雷达卡




京公网安备 11010802022788号







