Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems

Traditionally, industrial control systems (ICS) are closed structures that rely on specialized hardware and software with proprietary control protocols. However, with the advancement of technology and the digitalization of ICS, the attack space available to malicious actors has significantly expande...

Full description

Saved in:
Bibliographic Details
Main Authors: Ka-Kyung Kim, Joon-Seok Kim, Ieck-Chae Euom
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10964214/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699996380692480
author Ka-Kyung Kim
Joon-Seok Kim
Ieck-Chae Euom
author_facet Ka-Kyung Kim
Joon-Seok Kim
Ieck-Chae Euom
author_sort Ka-Kyung Kim
collection DOAJ
description Traditionally, industrial control systems (ICS) are closed structures that rely on specialized hardware and software with proprietary control protocols. However, with the advancement of technology and the digitalization of ICS, the attack space available to malicious actors has significantly expanded. Anomaly detection systems, initially implemented for detecting device faults or failures, have increasingly become the focus of research aimed at identifying attack patterns as cyberattack techniques become more sophisticated and intelligent. Many anomaly detection algorithms based on deep learning models have good performance but often involve complex neural network structures, creating a black-box issue where users cannot interpret the decisions made by the models. The black-box issue hinders the adoption of artificial intelligence (AI) systems that can ensure efficient and secure operation in ICS environments. Various attempts have been made to address the black box issue but limited to identifying the features that caused the anomaly. In detecting target anomalies in industrial control system operational data, it is important not only to identify feature importance, but also to consider correlations between variables, and to provide intuitive explanations to enhance the understanding of operators. To satisfy these major values, this paper proposes a method for explainable anomaly detection for ICS.
format Article
id doaj-art-ac409286311e4c80ad461a2e7e7efdd2
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ac409286311e4c80ad461a2e7e7efdd22025-08-20T03:18:24ZengIEEEIEEE Access2169-35362025-01-0113661706618710.1109/ACCESS.2025.356026010964214Explainable Anomaly Detection Based on Operational Sequences in Industrial Control SystemsKa-Kyung Kim0https://orcid.org/0009-0000-8750-1606Joon-Seok Kim1Ieck-Chae Euom2https://orcid.org/0000-0002-8224-1996System Security Research Center, Chonnam National University, Gwangju, South KoreaSystem Security Research Center, Chonnam National University, Gwangju, South KoreaSystem Security Research Center, Chonnam National University, Gwangju, South KoreaTraditionally, industrial control systems (ICS) are closed structures that rely on specialized hardware and software with proprietary control protocols. However, with the advancement of technology and the digitalization of ICS, the attack space available to malicious actors has significantly expanded. Anomaly detection systems, initially implemented for detecting device faults or failures, have increasingly become the focus of research aimed at identifying attack patterns as cyberattack techniques become more sophisticated and intelligent. Many anomaly detection algorithms based on deep learning models have good performance but often involve complex neural network structures, creating a black-box issue where users cannot interpret the decisions made by the models. The black-box issue hinders the adoption of artificial intelligence (AI) systems that can ensure efficient and secure operation in ICS environments. Various attempts have been made to address the black box issue but limited to identifying the features that caused the anomaly. In detecting target anomalies in industrial control system operational data, it is important not only to identify feature importance, but also to consider correlations between variables, and to provide intuitive explanations to enhance the understanding of operators. To satisfy these major values, this paper proposes a method for explainable anomaly detection for ICS.https://ieeexplore.ieee.org/document/10964214/Anomaly detectioncyber physical systemexplainable artificial intelligenceindustrial control systemoperational sequencetime-series feature
spellingShingle Ka-Kyung Kim
Joon-Seok Kim
Ieck-Chae Euom
Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
IEEE Access
Anomaly detection
cyber physical system
explainable artificial intelligence
industrial control system
operational sequence
time-series feature
title Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
title_full Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
title_fullStr Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
title_full_unstemmed Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
title_short Explainable Anomaly Detection Based on Operational Sequences in Industrial Control Systems
title_sort explainable anomaly detection based on operational sequences in industrial control systems
topic Anomaly detection
cyber physical system
explainable artificial intelligence
industrial control system
operational sequence
time-series feature
url https://ieeexplore.ieee.org/document/10964214/
work_keys_str_mv AT kakyungkim explainableanomalydetectionbasedonoperationalsequencesinindustrialcontrolsystems
AT joonseokkim explainableanomalydetectionbasedonoperationalsequencesinindustrialcontrolsystems
AT ieckchaeeuom explainableanomalydetectionbasedonoperationalsequencesinindustrialcontrolsystems