Adversarial Examples Detection with Bayesian Neural Network

arXiv:2105.08620v3 Announce Type: replace-cross
Abstract: In this paper, we propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors and make it easier to simulate the output distribution of a deep neural network. With these observations, we propose a novel Bayesian adversarial example detector, short for BATer, to improve the performance of adversarial example detection. Specifically, we study the distributional difference of hidden layer output between natural and adversarial …

abstract adversarial adversarial examples arxiv bayesian components cs.cv cs.lg deep neural network detection distribution examples framework network neural network novel paper random stat.ml type