Anomaly detection aims to detect abnormal events by a model of normality. It
plays an important role in many domains such as network intrusion detection,
criminal activity identity and so on. With the rapidly growing size of
accessible training data and high computation capacities, deep learning based
anomaly detection has become more and more popular. In this paper, a new
domain-based anomaly detection method based on generative adversarial networks
(GAN) is proposed. Minimum likelihood regularization is proposed to make the
generator produce more anomalies and prevent it from converging to normal data
distribution. Proper ensemble of anomaly scores is shown to improve the
stability of discriminator effectively. The proposed method has achieved
significant improvement than other anomaly detection methods on Cifar10 and UCI
datasets.
Description
Anomaly Detection via Minimum Likelihood Generative Adversarial Networks
%0 Generic
%1 wang2018anomaly
%A Wang, Chu
%A Zhang, Yan-Ming
%A Liu, Cheng-Lin
%D 2018
%K anomaly-detection gan
%T Anomaly Detection via Minimum Likelihood Generative Adversarial Networks
%U http://arxiv.org/abs/1808.00200
%X Anomaly detection aims to detect abnormal events by a model of normality. It
plays an important role in many domains such as network intrusion detection,
criminal activity identity and so on. With the rapidly growing size of
accessible training data and high computation capacities, deep learning based
anomaly detection has become more and more popular. In this paper, a new
domain-based anomaly detection method based on generative adversarial networks
(GAN) is proposed. Minimum likelihood regularization is proposed to make the
generator produce more anomalies and prevent it from converging to normal data
distribution. Proper ensemble of anomaly scores is shown to improve the
stability of discriminator effectively. The proposed method has achieved
significant improvement than other anomaly detection methods on Cifar10 and UCI
datasets.
@misc{wang2018anomaly,
abstract = {Anomaly detection aims to detect abnormal events by a model of normality. It
plays an important role in many domains such as network intrusion detection,
criminal activity identity and so on. With the rapidly growing size of
accessible training data and high computation capacities, deep learning based
anomaly detection has become more and more popular. In this paper, a new
domain-based anomaly detection method based on generative adversarial networks
(GAN) is proposed. Minimum likelihood regularization is proposed to make the
generator produce more anomalies and prevent it from converging to normal data
distribution. Proper ensemble of anomaly scores is shown to improve the
stability of discriminator effectively. The proposed method has achieved
significant improvement than other anomaly detection methods on Cifar10 and UCI
datasets.},
added-at = {2018-12-06T17:30:50.000+0100},
author = {Wang, Chu and Zhang, Yan-Ming and Liu, Cheng-Lin},
biburl = {https://www.bibsonomy.org/bibtex/2469ea965e241ad54b176ad9f307c04b6/daschloer},
description = {Anomaly Detection via Minimum Likelihood Generative Adversarial Networks},
interhash = {e6137a5cee91f65bce2f2f9ada60763f},
intrahash = {469ea965e241ad54b176ad9f307c04b6},
keywords = {anomaly-detection gan},
note = {cite arxiv:1808.00200},
timestamp = {2018-12-06T17:30:50.000+0100},
title = {Anomaly Detection via Minimum Likelihood Generative Adversarial Networks},
url = {http://arxiv.org/abs/1808.00200},
year = 2018
}