Deep Adversarial Learning Latent Representation Distribution Model for Anomaly Detection

XI Liang; LIU Han; FAN Hao-yi; ZHANG Feng-bin

doi:10.12263/DZXB.20200970

您当前的位置：

首页 >

文章列表页 >

Deep Adversarial Learning Latent Representation Distribution Model for Anomaly Detection

PAPERS | 更新时间：2025-12-08

- Deep Adversarial Learning Latent Representation Distribution Model for Anomaly Detection
- ACTA ELECTRONICA SINICA Vol. 49, Issue 7, Pages: 1257-1265(2021)
- 作者机构：
  
  哈尔滨理工大学计算机科学与技术学院, 黑龙江哈尔滨 150080
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20200970
  CLC： TP183
- Received：03 September 2020，
  
  Revised：2021-02-20，
  
  Published：25 July 2021
- 稿件说明：
移动端阅览
席亮,刘涵,樊好义等.基于深度对抗学习潜在表示分布的异常检测模型[J].电子学报,2021,49(07):1257-1265.

XI Liang,LIU Han,FAN Hao-yi,et al.Deep Adversarial Learning Latent Representation Distribution Model for Anomaly Detection[J].ACTA ELECTRONICA SINICA,2021,49(07):1257-1265.
席亮,刘涵,樊好义等.基于深度对抗学习潜在表示分布的异常检测模型[J].电子学报,2021,49(07):1257-1265. DOI： 10.12263/DZXB.20200970.

XI Liang,LIU Han,FAN Hao-yi,et al.Deep Adversarial Learning Latent Representation Distribution Model for Anomaly Detection[J].ACTA ELECTRONICA SINICA,2021,49(07):1257-1265. DOI： 10.12263/DZXB.20200970.

摘要

针对已有的异常检测模型在高维、样本多样(类内多样)的数据背景下无法获得合理的潜在表示分布，不平衡数据较多(正常数据远大于异常数据)时特征提取准确性低，以及分类器超参数敏感等问题，本文提出一种基于深度对抗学习潜在表示分布的异常检测模型. 基于正则化约束改进自编码器，将数据的原始特征空间映射到潜在特征空间形成低维的潜在表示，使其保持合理的空间分布；配以基于多判别器的生成对抗网络，在有效避免重构特征循环不一致和训练不稳定的基础上，来精确估计潜在表示的概率分布；以获得的潜在表示概率分布为单类分类器的输入，解决单类分类器超参数敏感问题，从而有效提高异常检测的整体性能.实验结果表明，相比于最新的基于机器学习和深度学习的异常检测模型，本文模型可在高维、样本多样、不平衡数据较多的应用背景下获得更合理的潜在表示空间分布并有效估计其概率分布，对单类分类器的超参数不敏感，并有效提高模型的检测性能.

Abstract

To solve the problems of the existing anomaly detection models

such as incoherent latent representation distribution under in high‑dimensional and diverse(within each class) data background

the low accuracy of feature extraction when unbalanced data(normal data far outweighs abnormal data) is large

and the sensitivity of classifier’s hyperparameter

a deep adversarial learning latent representation distribution model for anomaly detection is proposed. Based on the regularization constraint

an improved autoencoder can map the original data feature space to a low‑dimensional the latent feature space to get the reasonable latent representation distribution. On the premise of avoiding the problems of circulation inconsistent of reconstruction feature and unstable training

the multi‑discriminator‑based generative adversarial network can evaluate the latent representation probability distribution accurately

and to solve the hyperparameter sensitivity of one class classifier

so as to improve the overall performances of anomaly detection. Experimental results show that

compared with the up‑to‑date anomaly detection models based on machine learning and deep learning

the proposed model can obtain more coherent space distribution and ideal probability distribution of latent representation

is not sensitive to the hyperparameters of the single‑class classifier

and effectively improve the detection performances under the application background with high‑dimensional

diverse

unbalanced data.

关键词

Keywords

references

梅御东，陈旭，孙毓忠，等 . 一种基于日志信息和CNN‑ text的软件系统异常检测方法［J］. 计算机学报， 2020 ， 43 （ 02 ）： 366 - 380 .

MEI Yu‑dong ， CHEN Xu ， SUN Yu‑zhong ， et al . A method for software system anomaly detection based on log information and CNN‑Text ［J］. Chinese Journal of Computers ， 2020 ， 43 （ 02 ）： 366 - 380 . （in Chinese）

闻佳，王宏君，邓佳，刘鹏飞 . 基于深度学习的异常事件检测［J］. 电子学报， 2020 ， 48 （ 2 ）： 308 - 313 .

WEN Jia ， WANG Hong‑jun ， DENG Jia ， LIU Peng‑fei . Abnormal event detection based on deep learning ［J］. Acta Electronica Sinica ， 2020 ， 48 （ 2 ）： 308 - 313 . （in Chinese）

Pauwels E J ， Ambekar O . One class classification for anomaly detection： support vector data description revisited ［A］. Proceedings of the 11th Industrial Conference on Data Mining： Applications and Theoretical Aspects ［C］. New York， USA ： Springer ， 2011 . 25 - 39 .

Zhang M ， Xu B ， Gong J . An anomaly detection model based on one‑class SVM to detect network intrusions ［A］. Proceedings of the 11th International Conference on Mobile Ad‑hoc and Sensor Networks ［C］. Shenzhen， China ： IEEE ， 2015 . 102 - 107 .

Erfani ， Sarah M ， Baktashmotlagh ， Mahsa ， Rajasegarar ， Sutharshan . R1SVM： a randomised nonlinear approach to large‑scale anomaly detection ［A］. Proceedings of the 29th AAAI Conference on Artificial Intelligence ［C］. Austin， Texas， USA ： AAAI ， 2015 . 1 - 7 .

Bengio Y ， Courville A ， Vincent P . Representation learning： a review and new perspectives ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2013 ， 35 （ 8 ）： 1798 - 1828 .

Sakurada M ， Yairi T . Anomaly detection using autoencoders with nonlinear dimensionality reduction ［A］. Proceedings of the 2nd Workshop on Machine Learning for Sensory Data Analysis ［C］. Gold Coast， Australia ： ACM ， 2014 . 4 - 11 .

Nicolau M ， McDermott J . Learning neural representations for network anomaly detection ［J］. IEEE Transactions on Cybernetics ， 2018 ， 49 （ 8 ）： 3074 - 3087 .

Akcay S ， Atapour‑Abarghouei A ， Breckon T P . GANomaly： Semi‑supervised anomaly detection via adversarial training ［A］. Proceedings of the 14th Asian Conference on Computer Vision ［C］. Perth， Australia ： Springer ， 2018 . 622 - 637 .

Ngo P C ， Winarto A A ， Kou C ， et al . Fence GAN： towards better anomaly detection ［A］. Proceedings of the IEEE 31st International Conference on Tools with Artificial Intelligence ［C］. Portland， OR， USA ： IEEE ， 2019 . 141 - 148 .

Jiang W ， Hong Y ， Zhou B ， et al . A GAN‑based anomaly detection approach for imbalanced industrial time series ［J］. IEEE Access ， 2019 ， 7 ： 143608 - 143619 .

Malaiya R K ， Kwon D ， Kim J ， et al . An empirical evaluation of deep learning for network anomaly detection ［A］. Proceedings of the 2018 International Conference on Computing ， Networking and Communications［C］. Maui ， HI， USA ： IEEE ， 2018 . 893 - 898 .

Zhang C ， Song D ， Chen Y ， et al . A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data ［A］. Proceedings of the 34th AAAI Conference on Artificial Intelligence ［C］. New York， USA ： AAAI ， 2019 . 1409 - 1416 .

Zong B ， Song Q ， Min M R ， et al . Deep autoencoding Gaussian mixture model for unsupervised anomaly detection ［A］. Proceedings of the 6th International Conference on Learning Representations ［C］. Vancouver， BC， Canada ： OpenReview ， 2018 . 1 - 19 .

Li D ， Chen D ， Jin B ， et al . MAD‑GAN： Multivariate anomaly detection for time series data with generative adversarial networks ［A］. Proceedings of the 28th International Conference on Artificial Neural Networks ［C］. Munich， Germany ： Springer ， 2019 . 703 - 716 .

Kumarage T ， Ranathunga S ， Kuruppu C ， et al . Generative adversarial networks （GAN） based anomaly detection in industrial software systems ［A］. Proceedings of the 2019 Moratuwa Engineering Research Conference ［C］. Moratuwa， Sri Lanka ： IEEE ， 2019 . 43 - 48 .

Schlegl T ， Seeböck P ， Waldstein S M ， et al . f‑AnoGAN： Fast unsupervised anomaly detection with generative adversarial networks ［J］. Medical image analysis ， 2019 ， 54 ： 30 - 44 .

Li C ， Liu H ， Chen C ， et al . Alice： Towards understanding adversarial learning for joint distribution matching ［A］. Proceedings of the 31st Annual Conference on Neural Information Processing Systems ［C］. Long Beach， USA ： ACM ， 2017 . 5495 - 5503 .

Sarmiento A ， Fondón Irene ， Durán‑Díaz Iván ， et al . Centroid⁃based clustering with αβ‑divergences ［J］. Entropy ， 2019 ， 21 （ 2 ）： ArticleID： 196.

Moustafa N ， Slay J . UNSW‑NB15： a comprehensive data set for network intrusion detection systems （UNSW‑NB15 network data set）［A］. Proceedings of the 2015 Military Communications and Information Systems Conference ［C］. Canberra， ACT， Australia ： IEEE ， 2015 . 1 - 6 .

Amarnath B ， Balamurugan S A A . Review on feature selection techniques and its impact for effective data classification using UCI machine learning repository dataset ［J］. Journal of Engineering Science and Technology ， 2016 ， 11 （ 11 ）： 1639 - 1646 .

DeCamilla J ， Xia X ， Wang M ， et al . The multiple arrhythmia dataset evaluation database （MADAE）［J］. Journal of Electrocardiology ， 2018 ， 51 （ 6 ）： S106 - S112 .

Fujioka T ， Kubota K ， Mori M ， et al . Efficient anomaly detection with generative adversarial network for breast ultrasound imaging ［J］. Diagnostics ， 2020 ， 10 （ 7 ）：ArticleID： 456.

Zhao H ， Liu H ， Hu W ， et al . Anomaly detection and fault anAlysis of Wind tuRbine components based on deep learning network ［J］. Renewable Energy ， 2018 ， 127 ： 825 - 834 .

Seyed‑Allaei H . Phase diagram of spiking neural networks ［J］. Frontiers in Computational Neuroscience ， 2015 ， 9： ArticleID： 19.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Object Detection Based on EIMYOLO for High-Resolution Remote Sensing Images

A Survey of Network Attack Investigation Based on Provenance Graph

Related Author

HUANG Yu-zhe

GUAN Yong-yuan

WEI Song-jie

CAO Feng

ZENG Ke-wen

LI De-yu

LUO Xi-zhao

TAO Chong-ben

Related Institution

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

School of Information and Technology, Shanxi University

School of Computer Science and Technology, Soochow University

School of Electronics and Information Engineering, Suzhou University of Science and Technology

Cyberspace Institute of Advanced Technology, Guangzhou University

⁰