Chatillon, PierrickBallester, Coloma2020-09-022020Chatillon P, Ballester C. History-based anomaly detector: an adversarial approach to anomaly detection. In: Arai K, Kapoor S, Bhatia R, editors. Intelligent Systems and Applications. Proceedings of the 2020 Intelligent Systems Conference (IntelliSys). Volume 1. 2020 Sept 3-4. Cham: Springer; 2020. p. 761-76. (AISC; no. 1250). DOI: 10.1007/978-3-030-55180-3_58978-3-030-55179-7http://hdl.handle.net/10230/45245Comunicació presentada a: the 2020 Intelligent Systems Conference (IntelliSys), celebrada en línia el 3 i 4 de setembre de 2020.Anomaly detection is a difficult problem in many areas and has recently been subject to a lot of attention. Classifying unseen data as anomalous is a challenging matter. Latest proposed methods rely on Generative Adversarial Networks (GANs) to estimate the normal data distribution, and produce an anomaly score prediction for any given data. In this article, we propose a simple yet new adversarial method to tackle this problem, denoted as History-based anomaly detector (HistoryAD). It consists of a self-supervised model, trained to recognize ‘normal’ samples by comparing them to samples based on the training history of a previously trained GAN. Quantitative and qualitative results are presented evaluating its performance. We also present a comparison to several state-of-the-art methods for anomaly detection showing that our proposal achieves top-tier results on several datasets.application/pdfeng© Springer The final publication is available at Springer via https://doi.org/10.1007/978-3-030-55180-3_58info:eu-repo/semantics/conferenceObjecthttps://doi.org/10.1007/978-3-030-55180-3_58Anomaly detectionGenerative adversarial networksWasserstein and total variation distancesinfo:eu-repo/semantics/openAccess