基于最小化重构误差的生成对抗网络异常检测

王焕钢; 李鑫; 张涛

doi:10.1631/FITEE.1700786

Your Location：

Home >

Browse articles >

基于最小化重构误差的生成对抗网络异常检测

2018 Special Issue on Artificial Intelligence 2.0: Theories and Applications | Updated：2022-05-19

- 基于最小化重构误差的生成对抗网络异常检测
  Enhanced Publication
- Generative adversarial network based novelty detection using minimized reconstruction error
- 信息与电子工程前沿（英文） 2018年19卷第1期页码：116-125
- Affiliations：
  
  Department of Automation, School of Information Science and Technology, Tsinghua University, Beijing 100084, China
- Author bio：
  
  Huan-gang WANG, E-mail: hgwang@tsinghua.edu.cn
- Funds：
- DOI：10.1631/FITEE.1700786
  中图分类号： TP391
- 纸质出版日期：2018-01，
  
  收稿日期：2017-11-24，
  
  修回日期：2018-01-26，
- Accepted：
Scan QR Code
王焕钢, 李鑫, 张涛. 基于最小化重构误差的生成对抗网络异常检测[J]. 信息与电子工程前沿（英文）, 2018,19(1):116-125.

HUAN-GANG WANG, XIN LI, TAO ZHANG. Generative adversarial network based novelty detection using minimized reconstruction error. [J]. Frontiers of information technology & electronic engineering, 2018, 19(1): 116-125.
王焕钢, 李鑫, 张涛. 基于最小化重构误差的生成对抗网络异常检测[J]. 信息与电子工程前沿（英文）, 2018,19(1):116-125. DOI： 10.1631/FITEE.1700786.

HUAN-GANG WANG, XIN LI, TAO ZHANG. Generative adversarial network based novelty detection using minimized reconstruction error. [J]. Frontiers of information technology & electronic engineering, 2018, 19(1): 116-125. DOI： 10.1631/FITEE.1700786.

摘要

生成对抗网络是机器学习领域近年来最令人瞩目的进展，它通过在二人零和博弈中达到纳什均衡来训练模型。生成对抗网络由一个生成器和一个判别器构成，二者通过对抗学习机制进行训练。本文引入并调查了生成对抗网络在异常检测中的应用。在训练阶段，生成对抗网络从正常数据中学习；然后，基于过去的未知数据，生成器和判别器可以通过学习到的决策边界，区分异常和正常模式。提出的基于生成对抗网络的异常检测方法在MNIST数字数据集和田纳西-伊斯曼标准数据集上的性能表现极具竞争力。

Abstract

Generative adversarial network (GAN) is the most exciting machine learning breakthrough in recent years

and it trains the learning model by finding the Nash equilibrium of a two-player zero-sum game. GAN is composed of a generator and a discriminator

both trained with the adversarial learning mechanism. In this paper

we introduce and investigate the use of GAN for novelty detection. In training

GAN learns from ordinary data. Then

using previously unknown data

the generator and the discriminator with the designed decision boundaries can both be used to separate novel patterns from ordinary patterns. The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman (TE) benchmark process compared with the PCA-based novelty detection methods using Hotelling's

$$T^2$$

and squared prediction error statistics.

关键词

生成对抗网络异常检测田纳西-伊斯曼过程

Keywords

Generative adversarial network (GAN)Novelty detectionTennessee Eastman (TE) process

references

M Abadi, , , D Andersen. . Learning to protect communications with adversarial neural cryptography. . https://arxiv.org/abs/1610.06918, , 2016. ..

M Arjovsky, , , S Chintala, , , L Bottou. . Wasserstein generative adversarial networks. . Int Conf on Machine Learning, , 2017. . p.214--223. . ..

D Berthelot, , , T Schumm, , , L Metz. . BEGAN: boundary equilibrium generative adversarial networks. . https://arxiv.org/abs/1703.10717, , 2017. ..

L Clifton, , , D Clifton, , , P Watkinson, , , 等. . Identification of patient deterioration in vital-sign data using one-class support vector machines. . Federated Conf on Computer Science and Information Systems, , 2011. . p.125--131. . ..

E Denton, , , S Chintala, , , R Fergus, , , 等. . Deep generative image models using a Laplacian pyramid of adversarial networks. . Advances in Neural Information Processing Systems, , 2015. . p.1486--1494. . ..

J Donahue, , , P Krähenbühl, , , T Darrell. . Adversarial feature learning. . https://arxiv.org/abs/1605.09782, , 2016. ..

J Downs, , , E Vogel. . A plant-wide industrial process control problem. . Comput Chem Eng, , 1993. . 17((3):):245--255. . DOI:10.1016/0098-1354(93)80018-Ihttp://doi.org/10.1016/0098-1354(93)80018-I..

V Dumoulin, , , I Belghazi, , , B Poole, , , 等. . Adversarially learned inference. . https://arxiv.org/abs/1606.00704, , 2016. ..

Z Ge, , , Z Song. . Bagging support vector data description model for batch process monitoring. . J Proc Contr, , 2013. . 23((8):):1090--1096. . DOI:10.1016/j.jprocont.2013.06.010http://doi.org/10.1016/j.jprocont.2013.06.010..

Z Ge, , , C Yang, , , Z Song. . Improved kernel PCA-based monitoring approach for nonlinear processes. . Chem Eng Sci, , 2009. . 64((9):):2245--2255. . DOI:10.1016/j.ces.2009.01.050http://doi.org/10.1016/j.ces.2009.01.050..

Z Ge, , , F Gao, , , Z Song. . Batch process monitoring based on support vector data description method. . J Proc Contr, , 2011. . 21((6):):949--959. . DOI:10.1016/j.jprocont.2011.02.004http://doi.org/10.1016/j.jprocont.2011.02.004..

Z Ge, , , Z Song, , , F Gao. . Review of recent research on data-based process monitoring. . Ind Eng Chem Res, , 2013. . 52((10):):3543--3562. . DOI:10.1021/ie302069qhttp://doi.org/10.1021/ie302069q..

Z Ge, , , S Demyanov, , , Z Chen, , , 等. . Generative OpenMax for multi-class open set classification. . https://arxiv.org/abs/1707.07418, , 2017. ..

I Goodfellow, , , J Pouget-Abadie, , , M Mirza, , , 等. . Generative adversarial nets. . Advances in Neural Information Processing Systems, , 2014. . p.2672--2680. . ..

A Grover, , , S Ermon. . Boosted generative models. . https://arxiv.org/abs/1702.08484, , 2017. ..

V Hautamaki, , , I Karkkainen, , , P Franti. . Outlier detection using k-nearest neighbour graph. . Proc 17th Int Conf on Pattern Recognition, , 2004. . p.430--433. . DOI:10.1109/ICPR.2004.1334558http://doi.org/10.1109/ICPR.2004.1334558..

Z He, , , S Deng, , , X Xu. . An optimization model for outlier detection in categorical data. . LNCS, , 2005. . 3644400--409. . DOI:10.1007/11538059_42http://doi.org/10.1007/11538059_42..

H Hoffmann. . Kernel PCA for novelty detection. . Patt Recogn, , 2007. . 40((3):):863--874. . DOI:10.1016/j.patcog.2006.07.009http://doi.org/10.1016/j.patcog.2006.07.009..

A Kadurin, , , A Aliper, , , A Kazennov, , , 等. . The cornucopia of meaningful leads: applying deep adversarial autoencoders for new molecule development in oncology. . Oncotarget, , 2017a. . 8((7):):10883DOI:10.18632/oncotarget.14073http://doi.org/10.18632/oncotarget.14073..

A Kadurin, , , S Nikolenko, , , K Khrabrov, , , 等. . druGAN: an advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. . Mol Pharmaceut, , 2017b. . 14((9):):3098--3104. . DOI:10.1021/acs.molpharmaceut.7b00346http://doi.org/10.1021/acs.molpharmaceut.7b00346..

E Keogh, , , S Lonardi, , , C Ratanamahatana. . Towards parameter-free data mining. . Proc 10th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, , 2004. . p.206--215. . DOI:10.1145/1014052.1014077http://doi.org/10.1145/1014052.1014077..

T Kim, , , M Cha, , , H Kim, , , 等. . Learning to discover cross-domain relations with generative adversarial networks. . https://arxiv.org/abs/1703.05192, , 2017. ..

C Ledig, , , L Theis, , , F Huszár, , , 等. . Photo-realistic single image super-resolution using a generative adversarial network. . https://arxiv.org/abs/1609.04802, , 2016. ..

J Li, , , X Liang, , , Y Wei, , , 等. . Perceptual generative adversarial networks for small object detection. . CVPR, , 2017. . p.1951--1959. . DOI:10.1109/CVPR.2017.211http://doi.org/10.1109/CVPR.2017.211..

Y Li, , , L Maguire. . Selecting critical patterns based on local geometrical and statistical information. . IEEE Trans Patt Anal Mach Intell, , 2011. . 33((6):):1189--1201. . DOI:10.1109/TPAMI.2010.188http://doi.org/10.1109/TPAMI.2010.188..

Y Li, , , S Liu, , , J Yang, , , 等. . Generative face completion. . CVPR,, , 2017. . p.5892--5900. . DOI:10.1109/CVPR.2017.624http://doi.org/10.1109/CVPR.2017.624..

P Luc, , , C Couprie, , , S Chintala, , , 等. . Semantic segmentation using adversarial networks. . https://arxiv.org/abs/1611.08408, , 2016. ..

S Mahadevan, , , S Shah. . Fault detection and diagnosis in process data using one-class support vector machines. . J Proc Contr, , 2009. . 19((10):):1627--1639. . DOI:10.1016/j.jprocont.2009.07.011http://doi.org/10.1016/j.jprocont.2009.07.011..

X Mao, , , Q Li, , , H Xie, , , 等. . Least squares generative adversarial networks. . https://arxiv.org/abs/1611.04076, , 2016. ..

O Mogren. . C-RNN-GAN: continuous recurrent neural networks with adversarial training. . https://arxiv.org/abs/1611.09904, , 2016. ..

A Patcha, , , J Park. . An overview of anomaly detection techniques: existing solutions and latest technological trends. . Comput Netw, , 2007. . 51((12):):3448--3470. . DOI:10.1016/j.comnet.2007.02.001http://doi.org/10.1016/j.comnet.2007.02.001..

M Pimentel, , , D Clifton, , , L Clifton, , , 等. . A review of novelty detection. . Signal Process, , 2014. . 99215--249. . DOI:10.1016/j.sigpro.2013.12.026http://doi.org/10.1016/j.sigpro.2013.12.026..

A Radford, , , L Metz, , , S Chintala. . Unsupervised representation learning with deep convolutional generative adversarial networks. . https://arxiv.org/abs/1511.06434, , 2015. ..

S Reed, , , Z Akata, , , X Yan, , , 等. . Generative adversarial text to image synthesis. . Proc 33rd Int Conf on Machine Learning, , 2016. . p.1060--1069. . ..

T Schlegl, , , P Seeböck, , , S Waldstein, , , 等. . Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. . Int Conf on Information Processing in Medical Imaging, , 2017. . p.146--157. . DOI:10.1007/978-3-319-59050-9_12http://doi.org/10.1007/978-3-319-59050-9_12..

J Springenberg. . Unsupervised and semi-supervised learning with categorical generative adversarial networks. . https://arxiv.org/abs/1511.06390, , 2015. ..

C Vondrick, , , H Pirsiavash, , , A Torralba. . Generating videos with scene dynamics. . Advances in Neural Information Processing Systems, , 2016. . p.613--621. . ..

J Wu, , , C Zhang, , , T Xue, , , 等. . Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. . Advances in Neural Information Processing Systems, , 2016. . p.82--90. . ..

Y Xiao, , , H Wang, , , W Xu, , , 等. . Robust one-class SVM for fault detection. . Chemometr Intell Lab Syst, , 2016. . 15115--25. . DOI:10.1016/j.chemolab.2015.11.010http://doi.org/10.1016/j.chemolab.2015.11.010..

Z Yang, , , W Chen, , , F Wang, , , 等. . Improving neural machine translation with conditional sequence generative adversarial nets. . https://arxiv.org/abs/1703.04887, , 2017. ..

R Yeh, , , C Chen, , , T Lim, , , 等. . Semantic image inpainting with perceptual and contextual losses. . https://arxiv.org/abs/1607.07539, , 2016. ..

Z Yi, , , H Zhang, , , P Gong, , , 等. . DualGAN: unsupervised dual learning for image-to-image translation. . https://arxiv.org/abs/1704.02510, , 2017. ..

J Yu. . Semiconductor manufacturing process monitoring using Gaussian mixture model and Bayesian method with local and nonlocal information. . IEEE Trans Semicond Manuf, , 2012. . 25((3):):480--493. . DOI:10.1109/TSM.2012.2192945http://doi.org/10.1109/TSM.2012.2192945..

J Yu, , , S Qin. . Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models. . AIChE J, , 2008. . 54((7):):1811--1829. . DOI:10.1002/aic.11515http://doi.org/10.1002/aic.11515..

J Yu, , , S Qin. . Multiway Gaussian mixture model based multiphase batch process monitoring. . Ind Eng Chem Res, , 2009. . 48((18):):8585--8594. . DOI:10.1021/ie900479ghttp://doi.org/10.1021/ie900479g..

L Yu, , , W Zhang, , , J Wang, , , 等. . SeqGAN: sequence generative adversarial nets with policy gradient. . 31st AAAI Conf on Artificial Intelligence, , 2017. . p.2852--2858. . ..

F Zhao, , , J Feng, , , J Zhao, , , 等. . Robust LSTMautoencoders for face de-occlusion in the wild. . IEEE Trans Image Process, , 2018. . 27((2):):778--790. . DOI:10.1109/TIP.2017.2771408http://doi.org/10.1109/TIP.2017.2771408..

J Zhao, , , M Mathieu, , , Y LeCun. . Energy-based generative adversarial network. . https://arxiv.org/abs/1609.03126, , 2016. ..

J Zhu, , , T Park, , , P Isola, , , 等. . Unpaired image-to-image translation using cycle-consistent adversarial networks. . https://arxiv.org/abs/1703.10593, , 2017. ..

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据