poster

Steps towards continual learning in multivariate time-series anomaly detection using variational autoencoders

Authors:

Gastón García González,

Pedro Casas,

A. Fernández,

G. GómezAuthors Info & Claims

IMC '22: Proceedings of the 22nd ACM Internet Measurement Conference

Pages 774 - 775

https://doi.org/10.1145/3517745.3563033

Published: 25 October 2022 Publication History

Get Access

Abstract

We present DC-VAE, an approach to network anomaly detection in multivariate time-series (MTS), using Variational Auto Encoders (VAEs) and Dilated Convolutional Neural Networks (CNN). DC-VAE detects anomalies in MTS data through a single model, exploiting temporal and spatial MTS information. We showcase DC-VAE in different MTS datasets, and portray its future application in a continual learning framework, exploiting the generative properties of the underlying generative model to deal with continuously evolving data, avoiding catastrophic forgetting. We showcase the functioning of DC-VAE in the event of concept drifts, and propose the application of a novel approach to generative-driven continual learning, introducing the Deep Generative Replay model.

References

[1]

Ane Blázquez-García, Angel Conde, Usue Mori, and Jose A. Lozano. 2021. A Review on Outlier/Anomaly Detection in Time Series Data. ACM Comput. Surv. 54, 3, Article 56 (April 2021), 33 pages.

Google Scholar

[2]

Diederik P Kingma and Max Welling. 2013. Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114 (2013).

Google Scholar

[3]

Anna Kuzina, Evgenii Egorov, and Evgeny Burnaev. 2021. BooVAE: Boosting Approach for Continual Learning of VAE. Advances in Neural Information Processing Systems 35 (2021).

Google Scholar

[4]

A. P. Mathur and N. O. Tippenhauer. 2016. SWaT: A Water Treatment Testbed for Research and Training on ICS Security. In IEEE International Workshop on Cyber-physical Systems for Smart Water Networks (CySWater). 31--36.

Google Scholar

[5]

Guansong Pang, Chunhua Shen, Longbing Cao, and Anton Van Den Hengel. 2021. Deep Learning for Anomaly Detection: A Review. ACM Comput. Surv. 54, 2, Article 38 (March 2021), 38 pages.

Digital Library

Google Scholar

[6]

Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual Learning with Deep Generative Replay. CoRR abs/1705.08690 (2017). arXiv:1705.08690

Digital Library

Google Scholar

Cited By

View all

Wang YSun L(2024)Energy-efficient dynamic sensor time series classification for edge health devicesComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108268254(108268)Online publication date: Sep-2024
https://doi.org/10.1016/j.cmpb.2024.108268
Ao SFayek H(2023)Continual Deep Learning for Time Series ModelingSensors10.3390/s2316716723:16(7167)Online publication date: 14-Aug-2023
https://doi.org/10.3390/s23167167
Wang RFei JZhang RGuo MQi ZLi X(2023)DRnet: Dynamic Retraining for Malicious Traffic Small-Sample Incremental LearningElectronics10.3390/electronics1212266812:12(2668)Online publication date: 14-Jun-2023
https://doi.org/10.3390/electronics12122668
Show More Cited By

Index Terms

Steps towards continual learning in multivariate time-series anomaly detection using variational autoencoders
1. Mathematics of computing
  1. Probability and statistics
    1. Statistical paradigms
      1. Time series analysis
2. Networks
  1. Network services
    1. Network monitoring

Recommendations

Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges
Abstract
Anomaly detection has recently been applied to various areas, and several techniques based on deep learning have been proposed for the analysis of multivariate time series. In this study, we classify the anomalies into three types, ...
Highlights
- The methods for anomaly detection on multivariate time series are reviewed.
- The ...
Learning conditional variational autoencoders with missing covariates
Abstract
Conditional variational autoencoders (CVAEs) are versatile deep latent variable models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes that the data samples ...
Graphical abstract

Display Omitted
Highlights
- An improved learning method for conditional VAEs and Gaussian process prior VAEs.
- The method is designed for non-temporal, temporal, and longitudinal data.
- Used an amortised variational distribution for learning missing auxiliary ...
Time-Series Aware Precision and Recall for Anomaly Detection: Considering Variety of Detection Result and Addressing Ambiguous Labeling
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge Management

We proposetime-series aware precision andrecall, which are appropriate for evaluating anomaly detection methods in time-series data. In time-series data, an anomaly corresponds toa series of instances. The conventional metrics, however, overlook this ...

Comments

Information & Contributors

Information

Published In

IMC '22: Proceedings of the 22nd ACM Internet Measurement Conference

October 2022

796 pages

ISBN:9781450392594

DOI:10.1145/3517745

General Chairs:
Chadi Barakat
Inria, Université Côte d'Azur
,
Cristel Pelsser
University of Strasbourg
,
Program Chairs:
Theophilus A. Benson
Brown University
,
David Choffnes
Northeastern University

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

In-Cooperation

USENIX Assoc: USENIX Assoc

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 October 2022

Check for updates

Author Tags

Qualifiers

Poster

Funding Sources

FFG Austria
ANII-FMV Uruguay
CSIC Uruguay
ANII Uruguay

Conference

IMC '22

Sponsor:

IMC '22: ACM Internet Measurement Conference

October 25 - 27, 2022

Nice, France

Acceptance Rates

Overall Acceptance Rate 277 of 1,083 submissions, 26%

Upcoming Conference

IMC '24

Sponsor:
sigcomm
sigcomm

ACM Internet Measurement Conference

November 4 - 6, 2024

Madrid , AA , Spain

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
275
Total Downloads

Downloads (Last 12 months)114
Downloads (Last 6 weeks)6

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Wang YSun L(2024)Energy-efficient dynamic sensor time series classification for edge health devicesComputer Methods and Programs in Biomedicine10.1016/j.cmpb.2024.108268254(108268)Online publication date: Sep-2024
https://doi.org/10.1016/j.cmpb.2024.108268
Ao SFayek H(2023)Continual Deep Learning for Time Series ModelingSensors10.3390/s2316716723:16(7167)Online publication date: 14-Aug-2023
https://doi.org/10.3390/s23167167
Wang RFei JZhang RGuo MQi ZLi X(2023)DRnet: Dynamic Retraining for Malicious Traffic Small-Sample Incremental LearningElectronics10.3390/electronics1212266812:12(2668)Online publication date: 14-Jun-2023
https://doi.org/10.3390/electronics12122668
González GCasas PFernández A(2023)Deep Generative Replay for Multivariate Time-Series Monitoring with Variational Autoencoders2023 7th Network Traffic Measurement and Analysis Conference (TMA)10.23919/TMA58422.2023.10199001(1-4)Online publication date: 26-Jun-2023
https://doi.org/10.23919/TMA58422.2023.10199001
González GCasas PFernández A(2023)Fake it till you Detect it: Continual Anomaly Detection in Multivariate Time-Series using Generative AI2023 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW)10.1109/EuroSPW59978.2023.00068(558-566)Online publication date: Jul-2023
https://doi.org/10.1109/EuroSPW59978.2023.00068

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges

Learning conditional variational autoencoders with missing covariates

Time-Series Aware Precision and Recall for Anomaly Detection: Considering Variety of Detection Result and Addressing Ambiguous Labeling