计算机科学 ›› 2021, Vol. 48 ›› Issue (6): 202-209.doi: 10.11896/jsjkx.200400083

• 人工智能 • 上一篇    下一篇

基于全局和局部判别对抗自编码器的异常检测方法

邢红杰, 郝忠   

  1. 河北大学数学与信息科学学院河北省机器学习与计算智能重点实验室 河北 保定071002
  • 收稿日期:2020-04-20 修回日期:2020-08-05 出版日期:2021-06-15 发布日期:2021-06-03
  • 通讯作者: 邢红杰(hjxing@hbu.edu.cn)
  • 基金资助:
    国家自然科学基金(61672205);河北省自然科学基金(F2017201020)

Novelty Detection Method Based on Global and Local Discriminative Adversarial Autoencoder

XING Hong-jie, HAO ZhongHebei   

  1. Key Laboratory of Machine Learning and Computational Intelligence,College of Mathematics and Information Science,Hebei University,Baoding,Hebei 071002,China
  • Received:2020-04-20 Revised:2020-08-05 Online:2021-06-15 Published:2021-06-03
  • About author:XING Hong-jie,born in 1976,Ph.D,professor,master supervisor.His main research interests include kernel me-thods,neural networks,novelty detection and ensemble learning.
  • Supported by:
    National Natural Science Foundation of China(61672205) and Natural Science Foundation of Hebei Province(F2017201020).

摘要: 生成式对抗神经网络(Generative Adversarial Nets,GAN)和对抗自编码器(Adversarial Autoencoder,AAE)被成功地应用于图像生成中。此外,对抗网络能够无监督地对样本中所包含的数据特征进行学习。然而,将传统的对抗网络应用于异常检测时取得的分类效果较差,有两个方面的原因:一是GAN属于生成式模型,但异常检测模型往往被归入判别式模型的范畴;二是现有的AAE以自编码器的中间向量作为判别输入,对数据的重构效果不够理想。基于此,提出了一种基于双判别器的AAE,并将其应用于解决异常检测问题。所提方法中的双判别器具有不同的判别能力,即局部判别能力和全局判别能力。在MNIST,Fashion-MNIST和CIFAR-10数据集上的实验结果表明,所提方法能够有效避免训练过程中出现模式崩溃的问题。此外,与相关方法进行对比,所提方法取得了更优的检测性能。

关键词: 对抗自编码器, 模式崩溃, 生成式对抗网络, 异常检测

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

中图分类号: 

  • TP391.4
[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.
[1] 徐天慧, 郭强, 张彩明.
基于全变分比分隔距离的时序数据异常检测
Time Series Data Anomaly Detection Based on Total Variation Ratio Separation Distance
计算机科学, 2022, 49(9): 101-110. https://doi.org/10.11896/jsjkx.210600174
[2] 李其烨, 邢红杰.
基于最大相关熵的KPCA异常检测方法
KPCA Based Novelty Detection Method Using Maximum Correntropy Criterion
计算机科学, 2022, 49(8): 267-272. https://doi.org/10.11896/jsjkx.210700175
[3] 王馨彤, 王璇, 孙知信.
基于多尺度记忆残差网络的网络流量异常检测模型
Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network
计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[4] 杜航原, 李铎, 王文剑.
一种面向电商网络的异常用户检测方法
Method for Abnormal Users Detection Oriented to E-commerce Network
计算机科学, 2022, 49(7): 170-178. https://doi.org/10.11896/jsjkx.210600092
[5] 徐国宁, 陈奕芃, 陈一鸣, 陈晋音, 温浩.
基于约束优化生成式对抗网络的数据去偏方法
Data Debiasing Method Based on Constrained Optimized Generative Adversarial Networks
计算机科学, 2022, 49(6A): 184-190. https://doi.org/10.11896/jsjkx.210400234
[6] 武玉坤, 李伟, 倪敏雅, 许志骋.
单类支持向量机融合深度自编码器的异常检测模型
Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder
计算机科学, 2022, 49(3): 144-151. https://doi.org/10.11896/jsjkx.210100142
[7] 冷佳旭, 谭明圮, 胡波, 高新波.
基于隐式视角转换的视频异常检测
Video Anomaly Detection Based on Implicit View Transformation
计算机科学, 2022, 49(2): 142-148. https://doi.org/10.11896/jsjkx.210900266
[8] 刘意, 毛莺池, 程杨堃, 高建, 王龙宝.
基于邻域一致性的异常检测序列集成方法
Locality and Consistency Based Sequential Ensemble Method for Outlier Detection
计算机科学, 2022, 49(1): 146-152. https://doi.org/10.11896/jsjkx.201000156
[9] 张叶, 李志华, 王长杰.
基于核密度估计的轻量级物联网异常流量检测方法
Kernel Density Estimation-based Lightweight IoT Anomaly Traffic Detection Method
计算机科学, 2021, 48(9): 337-344. https://doi.org/10.11896/jsjkx.200600108
[10] 郭奕杉, 刘漫丹.
基于时空轨迹数据的异常检测
Anomaly Detection Based on Spatial-temporal Trajectory Data
计算机科学, 2021, 48(6A): 213-219. https://doi.org/10.11896/jsjkx.201100193
[11] 管文华, 林春雨, 杨尚蓉, 刘美琴, 赵耀.
基于人体关节点的低头异常行人检测
Detection of Head-bowing Abnormal Pedestrians Based on Human Joint Points
计算机科学, 2021, 48(5): 163-169. https://doi.org/10.11896/jsjkx.200800214
[12] 刘立成, 徐一凡, 谢贵才, 段磊.
面向NoSQL数据库的JSON文档异常检测与语义消歧模型
Outlier Detection and Semantic Disambiguation of JSON Document for NoSQL Database
计算机科学, 2021, 48(2): 93-99. https://doi.org/10.11896/jsjkx.200900039
[13] 邹承明, 陈德.
高维大数据分析的无监督异常检测方法
Unsupervised Anomaly Detection Method for High-dimensional Big Data Analysis
计算机科学, 2021, 48(2): 121-127. https://doi.org/10.11896/jsjkx.191100141
[14] 石琳姗, 马创, 杨云, 靳敏.
基于SSC-BP神经网络的异常检测算法
Anomaly Detection Algorithm Based on SSC-BP Neural Network
计算机科学, 2021, 48(12): 357-363. https://doi.org/10.11896/jsjkx.201000086
[15] 杨月麟, 毕宗泽.
基于深度学习的网络流量异常检测
Network Anomaly Detection Based on Deep Learning
计算机科学, 2021, 48(11A): 540-546. https://doi.org/10.11896/jsjkx.201200077
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!