Challenges of machine learning based monitoring for industrial control system networks

Matti Mantere, Ilkka Uusitalo, Mirko Sailio, Sami Noponen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

18 Citations (Scopus)

Abstract

Detecting network intrusions and anomalies in industrial control systems is growing in urgency. Such systems used to be isolated but are now being connected to the outside world. Even in the case of isolated networks, privileged users may still present various threats to the system, either accidentally or intentionally. Also malfunctions in devices may cause anomalous traffic. Anomaly detection based network monitoring and intrusion detection systems could be capable of discerning normal and aberrant traffic in industrial control systems, detecting security incidents in an early phase. In this paper we discuss the challenges for such a monitoring system. One of the challenges is which features best differentiate between anomalous and normal behaviour. In the analysis, special focus is placed on this selection
Original languageEnglish
Title of host publicationProceedings
Subtitle of host publication 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012
Place of PublicationFukuoka, Japan
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages968-972
ISBN (Print)978-1-4673-0867-0, 978-0-7695-4652-0
DOIs
Publication statusPublished - 2012
MoE publication typeNot Eligible
Event26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012 - Fukuoka, Japan
Duration: 26 Mar 201229 Mar 2012

Conference

Conference26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012
Abbreviated titleWAINA 2012
CountryJapan
CityFukuoka
Period26/03/1229/03/12

Fingerprint

Learning systems
Control systems
Monitoring
Intrusion detection

Keywords

  • Industrial control
  • intrusion detection
  • machine learning
  • monitoring
  • production facilities
  • protocols

Cite this

Mantere, M., Uusitalo, I., Sailio, M., & Noponen, S. (2012). Challenges of machine learning based monitoring for industrial control system networks. In Proceedings: 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012 (pp. 968-972). Fukuoka, Japan: IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/WAINA.2012.135
Mantere, Matti ; Uusitalo, Ilkka ; Sailio, Mirko ; Noponen, Sami. / Challenges of machine learning based monitoring for industrial control system networks. Proceedings: 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. Fukuoka, Japan : IEEE Institute of Electrical and Electronic Engineers , 2012. pp. 968-972
@inproceedings{fc0a9fd2748241d5825fda9e7d61ef0c,
title = "Challenges of machine learning based monitoring for industrial control system networks",
abstract = "Detecting network intrusions and anomalies in industrial control systems is growing in urgency. Such systems used to be isolated but are now being connected to the outside world. Even in the case of isolated networks, privileged users may still present various threats to the system, either accidentally or intentionally. Also malfunctions in devices may cause anomalous traffic. Anomaly detection based network monitoring and intrusion detection systems could be capable of discerning normal and aberrant traffic in industrial control systems, detecting security incidents in an early phase. In this paper we discuss the challenges for such a monitoring system. One of the challenges is which features best differentiate between anomalous and normal behaviour. In the analysis, special focus is placed on this selection",
keywords = "Industrial control, intrusion detection, machine learning, monitoring, production facilities, protocols",
author = "Matti Mantere and Ilkka Uusitalo and Mirko Sailio and Sami Noponen",
note = "Project code: 41465",
year = "2012",
doi = "10.1109/WAINA.2012.135",
language = "English",
isbn = "978-1-4673-0867-0",
pages = "968--972",
booktitle = "Proceedings",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Mantere, M, Uusitalo, I, Sailio, M & Noponen, S 2012, Challenges of machine learning based monitoring for industrial control system networks. in Proceedings: 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. IEEE Institute of Electrical and Electronic Engineers , Fukuoka, Japan, pp. 968-972, 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012, Fukuoka, Japan, 26/03/12. https://doi.org/10.1109/WAINA.2012.135

Challenges of machine learning based monitoring for industrial control system networks. / Mantere, Matti; Uusitalo, Ilkka; Sailio, Mirko; Noponen, Sami.

Proceedings: 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. Fukuoka, Japan : IEEE Institute of Electrical and Electronic Engineers , 2012. p. 968-972.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Challenges of machine learning based monitoring for industrial control system networks

AU - Mantere, Matti

AU - Uusitalo, Ilkka

AU - Sailio, Mirko

AU - Noponen, Sami

N1 - Project code: 41465

PY - 2012

Y1 - 2012

N2 - Detecting network intrusions and anomalies in industrial control systems is growing in urgency. Such systems used to be isolated but are now being connected to the outside world. Even in the case of isolated networks, privileged users may still present various threats to the system, either accidentally or intentionally. Also malfunctions in devices may cause anomalous traffic. Anomaly detection based network monitoring and intrusion detection systems could be capable of discerning normal and aberrant traffic in industrial control systems, detecting security incidents in an early phase. In this paper we discuss the challenges for such a monitoring system. One of the challenges is which features best differentiate between anomalous and normal behaviour. In the analysis, special focus is placed on this selection

AB - Detecting network intrusions and anomalies in industrial control systems is growing in urgency. Such systems used to be isolated but are now being connected to the outside world. Even in the case of isolated networks, privileged users may still present various threats to the system, either accidentally or intentionally. Also malfunctions in devices may cause anomalous traffic. Anomaly detection based network monitoring and intrusion detection systems could be capable of discerning normal and aberrant traffic in industrial control systems, detecting security incidents in an early phase. In this paper we discuss the challenges for such a monitoring system. One of the challenges is which features best differentiate between anomalous and normal behaviour. In the analysis, special focus is placed on this selection

KW - Industrial control

KW - intrusion detection

KW - machine learning

KW - monitoring

KW - production facilities

KW - protocols

U2 - 10.1109/WAINA.2012.135

DO - 10.1109/WAINA.2012.135

M3 - Conference article in proceedings

SN - 978-1-4673-0867-0

SN - 978-0-7695-4652-0

SP - 968

EP - 972

BT - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

CY - Fukuoka, Japan

ER -

Mantere M, Uusitalo I, Sailio M, Noponen S. Challenges of machine learning based monitoring for industrial control system networks. In Proceedings: 26th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. Fukuoka, Japan: IEEE Institute of Electrical and Electronic Engineers . 2012. p. 968-972 https://doi.org/10.1109/WAINA.2012.135