Universal Data Anomaly Detection via Inverse Generative Adversary Network

Abstract--The problem of detecting data anomaly is considered. Under the null hypothesis that models anomaly-free da ta, measurements are assumed to be from an unknown distribution with some authenticated historical samples. Under the comp os-ite alternative hypothesis, measurements are from an unkno wn distribution positive distance away from the distribution under the null hypothesis. No training data are available for the distribution of anomaly data. A semi-supervised deep learn ing technique based on an inverse generative adversary network is proposed.