Evolutive Adversarially-Trained Bayesian Network Autoencoder for Interpretable Anomaly Detection

Jorge Casajús-Setién, Concha Bielza, Pedro Larrañaga
Proceedings of The 11th International Conference on Probabilistic Graphical Models, PMLR 186:397-408, 2022.

Abstract

Semi-supervised detection of outliers with only positive and unlabeled data, which is among the most frequent forms of the anomaly detection (AD) problem in real scenarios, requires for a model to capture the normal behaviour of data from a training set exclusively comprised of normal-labelled data, so new unseen data can be afterwards compared to the induced notion of normality to be flagged -or not- as anomalous. In modelling a certain pattern of behaviour, generative models such as generative-adversarial networks (GANs) have proved to have great performance. Thus, numerous AD algorithms with GANs at its core have been proposed, most of them powered by deep neural networks and relying on an autoencoder for the AD task. In the present work, a novel approach to semi-supervised AD with Bayesian networks using generative-adversarial training and an evolutive strategy is proposed, which aims to palliate the intrinsic lack of interpretability of deep neural networks. The proposed model is tested on a real-world AD problem in cybersecurity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v186-casajus-setien22a, title = {Evolutive Adversarially-Trained Bayesian Network Autoencoder for Interpretable Anomaly Detection}, author = {Casaj{\'u}s-Seti{\'e}n, Jorge and Bielza, Concha and Larra{\~n}aga, Pedro}, booktitle = {Proceedings of The 11th International Conference on Probabilistic Graphical Models}, pages = {397--408}, year = {2022}, editor = {Salmerón, Antonio and Rumı́, Rafael}, volume = {186}, series = {Proceedings of Machine Learning Research}, month = {05--07 Oct}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v186/casajus-setien22a/casajus-setien22a.pdf}, url = {https://proceedings.mlr.press/v186/casajus-setien22a.html}, abstract = {Semi-supervised detection of outliers with only positive and unlabeled data, which is among the most frequent forms of the anomaly detection (AD) problem in real scenarios, requires for a model to capture the normal behaviour of data from a training set exclusively comprised of normal-labelled data, so new unseen data can be afterwards compared to the induced notion of normality to be flagged -or not- as anomalous. In modelling a certain pattern of behaviour, generative models such as generative-adversarial networks (GANs) have proved to have great performance. Thus, numerous AD algorithms with GANs at its core have been proposed, most of them powered by deep neural networks and relying on an autoencoder for the AD task. In the present work, a novel approach to semi-supervised AD with Bayesian networks using generative-adversarial training and an evolutive strategy is proposed, which aims to palliate the intrinsic lack of interpretability of deep neural networks. The proposed model is tested on a real-world AD problem in cybersecurity.} }
Endnote
%0 Conference Paper %T Evolutive Adversarially-Trained Bayesian Network Autoencoder for Interpretable Anomaly Detection %A Jorge Casajús-Setién %A Concha Bielza %A Pedro Larrañaga %B Proceedings of The 11th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2022 %E Antonio Salmerón %E Rafael Rumı́ %F pmlr-v186-casajus-setien22a %I PMLR %P 397--408 %U https://proceedings.mlr.press/v186/casajus-setien22a.html %V 186 %X Semi-supervised detection of outliers with only positive and unlabeled data, which is among the most frequent forms of the anomaly detection (AD) problem in real scenarios, requires for a model to capture the normal behaviour of data from a training set exclusively comprised of normal-labelled data, so new unseen data can be afterwards compared to the induced notion of normality to be flagged -or not- as anomalous. In modelling a certain pattern of behaviour, generative models such as generative-adversarial networks (GANs) have proved to have great performance. Thus, numerous AD algorithms with GANs at its core have been proposed, most of them powered by deep neural networks and relying on an autoencoder for the AD task. In the present work, a novel approach to semi-supervised AD with Bayesian networks using generative-adversarial training and an evolutive strategy is proposed, which aims to palliate the intrinsic lack of interpretability of deep neural networks. The proposed model is tested on a real-world AD problem in cybersecurity.
APA
Casajús-Setién, J., Bielza, C. & Larrañaga, P.. (2022). Evolutive Adversarially-Trained Bayesian Network Autoencoder for Interpretable Anomaly Detection. Proceedings of The 11th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 186:397-408 Available from https://proceedings.mlr.press/v186/casajus-setien22a.html.

Related Material