基于全局和局部判别对抗自编码器的异常检测方法

doi:10.11896/jsjkx.200400083

Abstract

Abstract: Generative Adversarial Nets(GAN) and Adversarial Autoencoder(AAE) have been successfully applied to image ge-neration.Moreover,adversarial network can learn the data features contained within the given samples in an unsupervised manner.However,when the conventional adversarial networks are applied to novelty detection,they may obtain poor classification results.The reasons lie in two aspects.One is that GAN belongs to generative models,while novelty detection models are usually classified as discriminative models.The other is that the existing AAEs use the intermediate vectors of autoencoder as the discriminant inputs,which makes the reconstruction outcomes for the given data are not satisfying.Therefore,an AAE based on double discriminators is proposed to make it fit for tackling the novelty detection problems.The double discriminators of the proposed model have different discriminative capabilities,i.e.,local discriminative capability and global discriminative capability.Experimental results on datasets of MNIST,Fashion-MNIST and CIFAR-10 show that the proposed method can effectively avoid the mode collapse problem that may occur during training.In addition,in comparison with its related approaches,the proposed method achieves a better detection performance.

Key words: Adversarial autoencoder, Anomaly detection, Generative adversarial nets, Mode collapse

CLC Number:

TP391.4

XING Hong-jie, HAO ZhongHebei. Novelty Detection Method Based on Global and Local Discriminative Adversarial Autoencoder[J].Computer Science, 2021, 48(6): 202-209.

References

[1]PIMENTEL M A F,CLIFTON D A,CLIFTON L,et al.A review of novelty detection[J].Signal Processing,2014,99:215-249.
[2]DING X,LI Y,BELATRECHE A,et al.An experimental eva-luation of novelty detection methods[J].Neurocomputing,2014,135:313-327.
[3]CLIFTON L,CLIFTON D A,WATKINSON P J,et.al.Identification of patient deterioration in vital-sign data using one-class support vector machines[C]//Proceedings of the Federated Conference on Computer Science and Information Systems.2011:125-131.
[4]TARASSENKO L,CLIFTON D A,BANNISTERP R,et al.Novelty Detection[M].New Jersey:John Wiley & Sons,Ltd,2009:1-22.
[5]PATCHA A,PARK J M.An overview of anomaly detectiontechniques:existing solutions and latest technological trends[J].Computer Networks,2007,51(12):3448-3470.
[6]JYOTHSNA V,PRASAD VV R.A review of anomaly based intrusion detection systems[J].International Journal of Computer Applications,2011,28(7):26-35.
[7]DIEHL C P,HAMPSHIRE J B.Real-time object classification and novelty detection for collaborative video surveillance[C]//Proceedings of the International Joint Conference on Neural Networks.2002:2620-2625.
[8]MARKOU M,SINGH S.A neural network-based novelty detec-tor for image sequence analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(10):1664-1677.
[9]BASU S,BILENKO M,MOONEY R.A probabilistic frame-work for semi-supervised clustering[C]//Proceedings of the 10th ACM International Conference on Knowledge Discovery and Data Mining.2004:59-68.
[10]TAX D M J.One-class classification:concept learning in the absence of counter examples[D].Delft:Delft University of Technology,2001.
[11]PARK C,HUANG J Z,DING Y.A computable plug-in estimator of minimum volume sets for novelty detection[J].Operations Research,2010,58(5):1469-1480.
[12]JUSZCZAK P,TAX D M J,PEKALSKA E,et al.Minimumspanning tree based one-class classifier[J].Neurocomputing,2009,72(7/8/9):1859-1869.
[13]HODGE V,AUSTIN J.A survey of outlier detection metho-dologies[J].Artificial Intelligence Review,2004,22(2):85-126.
[14]MARKOU M,SINGH S.Novelty detection:a review-part 1:statistical approaches[J].Signal Processing,2003,83(12):2481-2497.
[15]MARKOU M,SINGH S.Novelty detection:a review-part 2:neural network based approaches[J].Signal Processing,2003,83(12):2499-2521.
[16]PAN Z S,CHEN B,MIU Z M,et al.One-Class classifier research[J].Acta Electronica Sinica,2009,37(11):2496-2503.
[17]CHALAPATHY R,CHAWLA S.Deep learning for anomalydetection:a survey[J].arXiv:1901.03407,2019.
[18]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative adversarial nets[C]//Advances in Neural Information Processing Systems.2014:2672-2680.
[19]WANG K F,GOU C,DUAN Y J,et al.Research progress and prospect of generative adversarial network GAN[J].Journal of Automation,2017,43(3):321-332.
[20]LIN Y L,DAI X Y,LI L,et al.The new frontier of artificial intelligence research:generative confrontation network[J].Journal of Automation,2018,44(5):775-792.
[21]CHENG X Y,XIE L,ZHU J X,et al.Overview of generative adversarial network GAN[J].Computer Science,2019,46(3):74-81.
[22]GUI J,SUN Z,WEN Y,et al.A review on generative adversarial networks:algorithms,theory,and applications[J].arXiv:2001.06937,2020.
[23]SABOKROU M,KHALOOEI M,FATHY M,et al.Adversa-rially learned one-class classifier for novelty detection[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2018:3379-3388.
[24]WANG C,ZHANG Y M,LIU C L.Anomaly detection via minimum likelihood generative adversarial networks[C]//Procee-dings of the 2018 24th International Conference on Pattern Re-cognition.2018:1121-1126.
[25]LIU H B,WU T B,SHEN J,et al.Advanced persistent threat detection based on generative adversarial networks and long short-term memory[J].Computer Science,2020,47(1):281-286.
[26]CHEN Z,YEO C K,LEE B S,et al.Autoencoder-based network anomaly detection[C]//Proceedings of the 2018 Wireless Telecommunications Symposium.2018:1-5.
[27]AN J,CHO S.Variational autoencoder based anomaly detection using reconstruction probability[Z/OL].Special Lecture on IE,2015:1-18.https://www.ixueshu.com/document/6c508f6082caaadb318947a18e7f9386.html.
[28]PRINCIPI E,VESPERINI F,SQUARTINI S,et al.Acousticnovelty detection with adversarial autoencoders[C]//Procee-dings of the 2017 International Joint Conference on Neural Networks.2017:3324-3330.
[29]WANG X,DU Y,LIN S,et al.adVAE:a self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection[J/OL].Knowledge-Based Systems,https://doi.org/10.1016/j.knosys.2019.105187.
[30]TAN M S,LYU X,DING L,et al.Deep denoising autoencoder anomaly detection method based on elastic net[J].Computer Engineering and Design,2020,41(6):1516-1521.
[31]NGUYEN T,LE T,VU H,et al.Dual discriminator generative adversarial nets[C]//Advances in Neural Information Proces-sing Systems.2017:2667-2677.
[32]MAKHZANI A,SHLENS J,JAITLY N,et al.Adversarialautoencoders[C]//Proceedings of the 4th International Confe-rence on Learning Representations.2016
[33]AKCAY S,ATAPOUR-ABARGHOUEI A,BRECKON T P.Ganomaly:semi-supervised anomaly detection via adversarial training[C]//Proceedings of the 14th Asian Conference on Computer Vision.2018:622-637.
[34]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[C]//Proceedings of
the IEEE.1998:2278-2324.
[35]XIAO H,RASUL K,VOLLGRAF R.Fashion-MNIST:a novel image dataset for benchmarking machine learning algorithms[J].arXiv:1708.07747,2017.
[36]KRIZHEVSKY A,HINTON G.Learning Multiple Layers ofFeatures from Tiny Images[R].Technical Report,2009.
[37]KINGMA D P,BA J.Adam:a method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representations.2015.
[38]WU M,YE J.A small sphere and large margin approach for novelty detection using training data with outliers[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(11):2088-2092.
[39]ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein ge-nerative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning.2017:214-223.

Related Articles 15

[1]	XU Tian-hui, GUO Qiang, ZHANG Cai-ming. Time Series Data Anomaly Detection Based on Total Variation Ratio Separation Distance [J]. Computer Science, 2022, 49(9): 101-110.
[2]	LIU Xin, WANG Jun, SONG Qiao-feng, LIU Jia-hao. Collaborative Multicast Proactive Caching Scheme Based on AAE [J]. Computer Science, 2022, 49(9): 260-267.
[3]	WANG Xin-tong, WANG Xuan, SUN Zhi-xin. Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network [J]. Computer Science, 2022, 49(8): 314-322.
[4]	DU Hang-yuan, LI Duo, WANG Wen-jian. Method for Abnormal Users Detection Oriented to E-commerce Network [J]. Computer Science, 2022, 49(7): 170-178.
[5]	SHEN Shao-peng, MA Hong-jiang, ZHANG Zhi-heng, ZHOU Xiang-bing, ZHU Chun-man, WEN Zuo-cheng. Three-way Drift Detection for State Transition Pattern on Multivariate Time Series [J]. Computer Science, 2022, 49(4): 144-151.
[6]	WU Yu-kun, LI Wei, NI Min-ya, XU Zhi-cheng. Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder [J]. Computer Science, 2022, 49(3): 144-151.
[7]	LENG Jia-xu, TAN Ming-pi, HU Bo, GAO Xin-bo. Video Anomaly Detection Based on Implicit View Transformation [J]. Computer Science, 2022, 49(2): 142-148.
[8]	ZHANG Ye, LI Zhi-hua, WANG Chang-jie. Kernel Density Estimation-based Lightweight IoT Anomaly Traffic Detection Method [J]. Computer Science, 2021, 48(9): 337-344.
[9]	QING Lai-yun, ZHANG Jian-gong, MIAO Jun. Temporal Modeling for Online Anomaly Detection [J]. Computer Science, 2021, 48(7): 206-212.
[10]	GUO Yi-shan, LIU Man-dan. Anomaly Detection Based on Spatial-temporal Trajectory Data [J]. Computer Science, 2021, 48(6A): 213-219.
[11]	ZOU Cheng-ming, CHEN De. Unsupervised Anomaly Detection Method for High-dimensional Big Data Analysis [J]. Computer Science, 2021, 48(2): 121-127.
[12]	SHI Lin-shan, MA Chuang, YANG Yun, JIN Min. Anomaly Detection Algorithm Based on SSC-BP Neural Network [J]. Computer Science, 2021, 48(12): 357-363.
[13]	YANG Yue-lin, BI Zong-ze. Network Anomaly Detection Based on Deep Learning [J]. Computer Science, 2021, 48(11A): 540-546.
[14]	FENG An-ran, WANG Xu-ren, WANG Qiu-yun, XIONG Meng-bo. Database Anomaly Access Detection Based on Principal Component Analysis and Random Tree [J]. Computer Science, 2020, 47(9): 94-98.
[15]	ZHONG Ying-yu, CHEN Song-can. High-order Multi-view Outlier Detection [J]. Computer Science, 2020, 47(9): 99-104.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Novelty Detection Method Based on Global and Local Discriminative Adversarial Autoencoder

PDF (PC)

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0