EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems

Bedeuro Kim iD, Mohsen Ali Alawami iD, Eunsoo Kim, Sanghak Oh, Jeongyong Park, Hyoungshick Kim iD

Sensors · 23.01.2023 · 23 (3) · 1310

DOI: 10.3390/s23031310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.01.2023. Verfasst von Bedeuro Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea. Die Arbeit wurde bisher 118-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Information & communications Technology Promotion (IITP).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly detection has been known as an effective technique to detect faults or cyber-attacks in industrial control systems (ICS). Therefore, many anomaly detection models have been proposed for ICS. However, most models have been implemented and evaluated under specific circumstances, which leads to confusion about choosing the best model in a real-world situation. In other words, there still needs to be a comprehensive comparison of state-of-the-art anomaly detection models with common experimental configurations. To address this problem, we conduct a comparative study of five representative time series anomaly detection models: InterFusion, RANSynCoder, GDN, LSTM-ED, and USAD. We specifically compare the performance analysis of the models in detection accuracy, training, and testing times with two publicly available datasets: SWaT and HAI. The experimental results show that the best model results are inconsistent with the datasets. For SWaT, InterFusion achieves the highest F1-score of 90.7% while RANSynCoder achieves the highest F1-score of 82.9% for HAI. We also investigate the effects of the training set size on the performance of anomaly detection models. We found that about 40% of the entire training set would be sufficient to build a model producing a similar performance compared to using the entire training set.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectiondeep learning modelindustrial control systemsintrusion detection systemsunsupervised learning

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea.
  • Department of Computer Science and Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea.

ORCID-Profile: Bedeuro Kim, Mohsen Ali Alawami, Hyoungshick Kim

Förderung

  • Institute for Information & communications Technology Promotion (IITP)

Zitieren

APA

Kim, B., Alawami, M. A., Kim, E., Oh, S., Park, J., & Kim, H. (2023). A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems. Sensors, 23(3), 1310. https://doi.org/10.3390/s23031310

Vancouver

Kim B, Alawami MA, Kim E, Oh S, Park J, Kim H. A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems. Sensors. 2023;23(3):1310. doi:10.3390/s23031310

BibTeX
@article{Kim2023,
  author = {Kim, Bedeuro and Alawami, Mohsen Ali and Kim, Eunsoo and Oh, Sanghak and Park, Jeongyong and Kim, Hyoungshick},
  title = {A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1310},
  doi = {10.3390/s23031310}
}
Kostenlos starten →