Home > Research > Publications & Outputs > Digital Twin-Enhanced Methodology for Training ...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications. / Allison, David; Smith, Paul; McLaughlin, Kieran.
2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022. IEEE, 2022. p. 226-232 (IEEE International Conference on Industrial Informatics (INDIN); Vol. 2022-July).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Allison, D, Smith, P & McLaughlin, K 2022, Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications. in 2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022. IEEE International Conference on Industrial Informatics (INDIN), vol. 2022-July, IEEE, pp. 226-232. https://doi.org/10.1109/INDIN51773.2022.9976095

APA

Allison, D., Smith, P., & McLaughlin, K. (2022). Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications. In 2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022 (pp. 226-232). (IEEE International Conference on Industrial Informatics (INDIN); Vol. 2022-July). IEEE. https://doi.org/10.1109/INDIN51773.2022.9976095

Vancouver

Allison D, Smith P, McLaughlin K. Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications. In 2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022. IEEE. 2022. p. 226-232. (IEEE International Conference on Industrial Informatics (INDIN)). Epub 2022 Jul 25. doi: 10.1109/INDIN51773.2022.9976095

Author

Allison, David ; Smith, Paul ; McLaughlin, Kieran. / Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications. 2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022. IEEE, 2022. pp. 226-232 (IEEE International Conference on Industrial Informatics (INDIN)).

Bibtex

@inproceedings{06b69e8e9e0c4dab98afc51ea9f68bc7,
title = "Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications.",
abstract = "Digital twins can address the problem of data scarcity during the training machine learning models, as they can be used to simulate and explore a range of process conditions and system states that are too difficult or dangerous to explore in real-world Cyber-Physical Systems (CPSs). Meanwhile, advances in industrial control systems technology have enabled increasingly complex functionality to be deployed on or near so-called edge devices, such as Programmable Logic Controllers (PLCs).In this paper, we propose a methodology for training a machine learning model offline using data extracted from a digital twin, before converting the model for deployment on an edge device to perform anomaly detection. To examine the model's suitability for anomaly detection, we execute several simulations of fault conditions. Results show that the model can successfully predict normal operations as well as identify faults and cyber-attacks. There is a negligible drop in performance on the edge device, when compared to executing the model on a personal computer, but it remains suitable for the application.",
keywords = "Cyber Security, Digital Twins, Edge Computing, Machine Learning",
author = "David Allison and Paul Smith and Kieran McLaughlin",
year = "2022",
month = dec,
day = "15",
doi = "10.1109/INDIN51773.2022.9976095",
language = "English",
series = "IEEE International Conference on Industrial Informatics (INDIN)",
publisher = "IEEE",
pages = "226--232",
booktitle = "2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022",

}

RIS

TY - GEN

T1 - Digital Twin-Enhanced Methodology for Training Edge-Based Models for Cyber Security Applications.

AU - Allison, David

AU - Smith, Paul

AU - McLaughlin, Kieran

PY - 2022/12/15

Y1 - 2022/12/15

N2 - Digital twins can address the problem of data scarcity during the training machine learning models, as they can be used to simulate and explore a range of process conditions and system states that are too difficult or dangerous to explore in real-world Cyber-Physical Systems (CPSs). Meanwhile, advances in industrial control systems technology have enabled increasingly complex functionality to be deployed on or near so-called edge devices, such as Programmable Logic Controllers (PLCs).In this paper, we propose a methodology for training a machine learning model offline using data extracted from a digital twin, before converting the model for deployment on an edge device to perform anomaly detection. To examine the model's suitability for anomaly detection, we execute several simulations of fault conditions. Results show that the model can successfully predict normal operations as well as identify faults and cyber-attacks. There is a negligible drop in performance on the edge device, when compared to executing the model on a personal computer, but it remains suitable for the application.

AB - Digital twins can address the problem of data scarcity during the training machine learning models, as they can be used to simulate and explore a range of process conditions and system states that are too difficult or dangerous to explore in real-world Cyber-Physical Systems (CPSs). Meanwhile, advances in industrial control systems technology have enabled increasingly complex functionality to be deployed on or near so-called edge devices, such as Programmable Logic Controllers (PLCs).In this paper, we propose a methodology for training a machine learning model offline using data extracted from a digital twin, before converting the model for deployment on an edge device to perform anomaly detection. To examine the model's suitability for anomaly detection, we execute several simulations of fault conditions. Results show that the model can successfully predict normal operations as well as identify faults and cyber-attacks. There is a negligible drop in performance on the edge device, when compared to executing the model on a personal computer, but it remains suitable for the application.

KW - Cyber Security

KW - Digital Twins

KW - Edge Computing

KW - Machine Learning

U2 - 10.1109/INDIN51773.2022.9976095

DO - 10.1109/INDIN51773.2022.9976095

M3 - Conference contribution/Paper

T3 - IEEE International Conference on Industrial Informatics (INDIN)

SP - 226

EP - 232

BT - 2022 IEEE 20th International Conference on Industrial Informatics, INDIN 2022

PB - IEEE

ER -