EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks

As industrial control network threats become increasingly complex, traditional intrusion detection systems (IDS) struggle to capture implicit relationships due to feature redundancy and intricate feature interactions. This leads to increased computational complexity and higher detection latency, mak...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinyang Liu, Guogang Wang, Xuejun Zong, Bowei Ning, Kan He
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10902390/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850071919076835328
author Jinyang Liu
Guogang Wang
Xuejun Zong
Bowei Ning
Kan He
author_facet Jinyang Liu
Guogang Wang
Xuejun Zong
Bowei Ning
Kan He
author_sort Jinyang Liu
collection DOAJ
description As industrial control network threats become increasingly complex, traditional intrusion detection systems (IDS) struggle to capture implicit relationships due to feature redundancy and intricate feature interactions. This leads to increased computational complexity and higher detection latency, making it difficult for industrial control systems(ICS) to meet the fast and accurate response requirements for security events. In this study, we propose a dynamic anomaly detection model for industrial control networks, named EfficientTransformer. The model uses a 1D Convolutional Neural Network (1D-CNN) to extract local features from the data, while a linear multi-head self-attention mechanism, replacing the traditional Transformer’s multi-head attention mechanism, provides global learning capabilities. This reduces computational complexity and enables efficient parallel learning. Additionally, to address the issue of class imbalance, the model incorporates a weighted cross-entropy loss function that assigns higher weights to the minority class of abnormal traffic, thereby improving the model’s anomaly detection ability. This innovation further mitigates issues of feature redundancy and complex feature interactions, enhancing the model’s dynamic processing capability and accuracy. The method was validated on the Oil and Gas Gathering and Transportation Full-Process Industrial Platform Attack-Defense Field, and the Catalytic Reforming Unit Process Platform at the Key Laboratory of Information Security for the Petrochemical Industry in Liaoning Province. Experimental results show that the proposed EfficientTransformer improves accuracy by 1.01% and 2.26% compared to the standard Transformer on the two datasets and significantly reduces testing time, demonstrating its applicability in the field of industrial information security.
format Article
id doaj-art-95dbaaf0b8c64932a5dc504ab09f5b2b
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-95dbaaf0b8c64932a5dc504ab09f5b2b2025-08-20T02:47:10ZengIEEEIEEE Access2169-35362025-01-0113379313794510.1109/ACCESS.2025.354565910902390EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control NetworksJinyang Liu0https://orcid.org/0009-0000-0211-865XGuogang Wang1Xuejun Zong2https://orcid.org/0009-0000-0084-2775Bowei Ning3Kan He4College of Information Engineering, Shenyang University of Chemical Technology, Shenyang, Liaoning, ChinaCollege of Information Engineering, Shenyang University of Chemical Technology, Shenyang, Liaoning, ChinaCollege of Information Engineering, Shenyang University of Chemical Technology, Shenyang, Liaoning, ChinaKey Laboratory of Information Security for Petrochemical Industry, Shenyang, Liaoning, ChinaCollege of Information Engineering, Shenyang University of Chemical Technology, Shenyang, Liaoning, ChinaAs industrial control network threats become increasingly complex, traditional intrusion detection systems (IDS) struggle to capture implicit relationships due to feature redundancy and intricate feature interactions. This leads to increased computational complexity and higher detection latency, making it difficult for industrial control systems(ICS) to meet the fast and accurate response requirements for security events. In this study, we propose a dynamic anomaly detection model for industrial control networks, named EfficientTransformer. The model uses a 1D Convolutional Neural Network (1D-CNN) to extract local features from the data, while a linear multi-head self-attention mechanism, replacing the traditional Transformer’s multi-head attention mechanism, provides global learning capabilities. This reduces computational complexity and enables efficient parallel learning. Additionally, to address the issue of class imbalance, the model incorporates a weighted cross-entropy loss function that assigns higher weights to the minority class of abnormal traffic, thereby improving the model’s anomaly detection ability. This innovation further mitigates issues of feature redundancy and complex feature interactions, enhancing the model’s dynamic processing capability and accuracy. The method was validated on the Oil and Gas Gathering and Transportation Full-Process Industrial Platform Attack-Defense Field, and the Catalytic Reforming Unit Process Platform at the Key Laboratory of Information Security for the Petrochemical Industry in Liaoning Province. Experimental results show that the proposed EfficientTransformer improves accuracy by 1.01% and 2.26% compared to the standard Transformer on the two datasets and significantly reduces testing time, demonstrating its applicability in the field of industrial information security.https://ieeexplore.ieee.org/document/10902390/Intrusion detectionindustrial control networktransformer1D-CNNfeature extraction
spellingShingle Jinyang Liu
Guogang Wang
Xuejun Zong
Bowei Ning
Kan He
EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
IEEE Access
Intrusion detection
industrial control network
transformer
1D-CNN
feature extraction
title EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
title_full EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
title_fullStr EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
title_full_unstemmed EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
title_short EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks
title_sort efficienttransformer a dynamic anomaly detection model for industrial control networks
topic Intrusion detection
industrial control network
transformer
1D-CNN
feature extraction
url https://ieeexplore.ieee.org/document/10902390/
work_keys_str_mv AT jinyangliu efficienttransformeradynamicanomalydetectionmodelforindustrialcontrolnetworks
AT guogangwang efficienttransformeradynamicanomalydetectionmodelforindustrialcontrolnetworks
AT xuejunzong efficienttransformeradynamicanomalydetectionmodelforindustrialcontrolnetworks
AT boweining efficienttransformeradynamicanomalydetectionmodelforindustrialcontrolnetworks
AT kanhe efficienttransformeradynamicanomalydetectionmodelforindustrialcontrolnetworks