Time Series Anomaly Detection using Diffusion-based Models

被引：11
作者：
Pintilie, Ioana [1 ,2 ]
Manolache, Andrei [1 ,3 ]
Brad, Florin [1 ]
机构：
[1] Bitdefender, Bucharest, Romania
[2] Univ Bucharest, Bucharest, Romania
[3] Univ Stuttgart, Stuttgart, Germany
来源：
2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023 | 2023年
关键词：
Anomaly Detection; Multivariate Time Series; Diffusion; SUPPORT;
D O I：
10.1109/ICDMW60847.2023.00080
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Diffusion models have been recently used for anomaly detection (AD) in images. In this paper we investigate whether they can also be leveraged for AD on multivariate time series (MTS). We test two diffusion-based models and compare them to several strong neural baselines. We also extend the PA%K protocol, by computing a ROCK-AUC metric, which is agnostic to both the detection threshold and the ratio K of correctly detected points. Our models outperform the baselines on synthetic datasets and are competitive on real-world datasets, illustrating the potential of diffusion-based methods for AD in multivariate time series.
引用
收藏
页码：570 / 578
页数：9
相关论文
共 50 条
[21]   GAN-Based Anomaly Detection for Multivariate Time Series Using Polluted Training Set [J].
Du, Bowen ;
Sun, Xuanxuan ;
Ye, Junchen ;
Cheng, Ke ;
Wang, Jingyuan ;
Sun, Leilei .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (12) :12208-12219
[22]   Time Series Anomaly Detection with Reconstruction-Based State-Space Models [J].
Wang, Fan ;
Wang, Keli ;
Yao, Boyu .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT III, 2023, 14256 :74-86
[23]   Multivariate Time Series Anomaly Detection with Fourier Time Series Transformer [J].
Ye, Yufeng ;
He, Qichao ;
Zhang, Peng ;
Xiao, Jie ;
Li, Zhao .
2023 IEEE 12TH INTERNATIONAL CONFERENCE ON CLOUD NETWORKING, CLOUDNET, 2023, :381-388
[24]   An anomaly detection model for multivariate time series with anomaly perception [J].
Wei, Dong ;
Sun, Wu ;
Zou, Xiaofeng ;
Ma, Dan ;
Xu, Huarong ;
Chen, Panfeng ;
Yang, Chaoshu ;
Chen, Mei ;
Li, Hui .
PEERJ COMPUTER SCIENCE, 2024, 10
[25]   An anomaly detection model for multivariate time series with anomaly perception [J].
Wei, Dong ;
Sun, Wu ;
Zou, Xiaofeng ;
Ma, Dan ;
Xu, Huarong ;
Chen, Panfeng ;
Yang, Chaoshu ;
Chen, Mei ;
Li, Hui .
PeerJ Computer Science, 2024, 10
[26]   Anomaly Scoring for Prediction-Based Anomaly Detection in Time Series [J].
Li, Tianyu ;
Comer, Mary L. ;
Delp, Edward J. ;
Desai, Sundip R. ;
Mathieson, James L. ;
Foster, Richard H. ;
Chan, Moses W. .
2020 IEEE AEROSPACE CONFERENCE (AEROCONF 2020), 2020,
[27]   Clustering-based anomaly detection in multivariate time series data [J].
Li, Jinbo ;
Izakian, Hesam ;
Pedrycz, Witold ;
Jamal, Iqbal .
APPLIED SOFT COMPUTING, 2021, 100
[28]   Semisupervised anomaly detection of multivariate time series based on a variational autoencoder [J].
Ningjiang Chen ;
Huan Tu ;
Xiaoyan Duan ;
Liangqing Hu ;
Chengxiang Guo .
Applied Intelligence, 2023, 53 :6074-6098
[29]   Anomaly Detection Method for Multivariate Time Series Data Based on BLTranAD [J].
Zhang, Chuanlei ;
Wu, Songlin ;
Gao, Ming ;
Li, Yubo ;
Shi, Gongcheng ;
Li, Yicong ;
Ma, Hui .
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT XIII, ICIC 2024, 2024, 14874 :16-26
[30]   Anomaly detection model for multivariate time series based on stochastic Transformer [J].
Huo W. ;
Liang R. ;
Li Y. .
Tongxin Xuebao/Journal on Communications, 2023, 44 (02) :94-103
12345