Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks

Abstract Cyber-physical system (CPS) security has become more important in the age of Industry 4.0 because of the quick integration of automation and the Internet of Things. The goal of this project is to create a strong intrusion detection and control system that can recognize and lessen security r...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang Yan, Piyush Kumar Shukla, Prashant Kumar Shukla, Kanika Thakur, Anurag Sinha, Saifullah Khalid
Format: Article
Language:English
Published: Springer 2025-06-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00890-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850207335809548288
author Zhang Yan
Piyush Kumar Shukla
Prashant Kumar Shukla
Kanika Thakur
Anurag Sinha
Saifullah Khalid
author_facet Zhang Yan
Piyush Kumar Shukla
Prashant Kumar Shukla
Kanika Thakur
Anurag Sinha
Saifullah Khalid
author_sort Zhang Yan
collection DOAJ
description Abstract Cyber-physical system (CPS) security has become more important in the age of Industry 4.0 because of the quick integration of automation and the Internet of Things. The goal of this project is to create a strong intrusion detection and control system that can recognize and lessen security risks in CPS settings. The suggested approach makes use of deep learning (DL) and reinforcement learning (RL) techniques. To guarantee data consistency, pre-processing procedures such as mean-based imputation and min–max scaling come after data collection. ADASYN data augmentation is used to address class imbalance, while entropy analysis and statistical techniques are used to extract key features. The intrusion detection phase uses a combination of deep convolutional neural networks (DCNN) and bidirectional long short-term memory (BI-LSTM) networks to capture both spatial and temporal relationships in the data, while a hybrid feature selection technique improves the model’s performance. A deep Q-network (DQN) handles attack mitigation and uses reinforcement learning to adjust to new threats. Detecting attack patterns with high sensitivity (0.984), specificity (0.983), and accuracy (0.991626) for dataset 1, the accuracy of dataset 2 is 0.985 for 70% of training and 0.988 for 80% of training, and the Proposed-DBID-Net architecture enhances CPS security in Industry 4.0. The evaluation phase emphasizes how crucial feature selection is to maximize the model’s accuracy. In conclusion, this study offers a thorough and flexible method for protecting CPS in Industry 4.0, guaranteeing accuracy and scalability across changing cyber threats.
format Article
id doaj-art-e33c43f379944cba8fce038f06fbb2aa
institution OA Journals
issn 1875-6883
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-e33c43f379944cba8fce038f06fbb2aa2025-08-20T02:10:32ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-06-0118113810.1007/s44196-025-00890-9Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-NetworksZhang Yan0Piyush Kumar Shukla1Prashant Kumar Shukla2Kanika Thakur3Anurag Sinha4Saifullah Khalid5Law and Public Management School, Leshan Normal UniversityDepartment of Computer Science and Engineering, University Institute of Technology, Rajiv Gandhi Proudyogiki Vishwavidyalaya (State Technological University of Madhya Pradesh)Professor, Department of Computer Science and Engineering & Deputy Dean Research(ASET), Amity School of Engineering and Technology (ASET), Amity UniversityDepartment of Computer Science and Engineering, Galgotias UniversityInstitute of Chartered Financial Analysts of India (ICFAI) UniversityIBMM ResearchAbstract Cyber-physical system (CPS) security has become more important in the age of Industry 4.0 because of the quick integration of automation and the Internet of Things. The goal of this project is to create a strong intrusion detection and control system that can recognize and lessen security risks in CPS settings. The suggested approach makes use of deep learning (DL) and reinforcement learning (RL) techniques. To guarantee data consistency, pre-processing procedures such as mean-based imputation and min–max scaling come after data collection. ADASYN data augmentation is used to address class imbalance, while entropy analysis and statistical techniques are used to extract key features. The intrusion detection phase uses a combination of deep convolutional neural networks (DCNN) and bidirectional long short-term memory (BI-LSTM) networks to capture both spatial and temporal relationships in the data, while a hybrid feature selection technique improves the model’s performance. A deep Q-network (DQN) handles attack mitigation and uses reinforcement learning to adjust to new threats. Detecting attack patterns with high sensitivity (0.984), specificity (0.983), and accuracy (0.991626) for dataset 1, the accuracy of dataset 2 is 0.985 for 70% of training and 0.988 for 80% of training, and the Proposed-DBID-Net architecture enhances CPS security in Industry 4.0. The evaluation phase emphasizes how crucial feature selection is to maximize the model’s accuracy. In conclusion, this study offers a thorough and flexible method for protecting CPS in Industry 4.0, guaranteeing accuracy and scalability across changing cyber threats.https://doi.org/10.1007/s44196-025-00890-9Cyber-physical systemsIndustry 4.0Intrusion detection and mitigationDeep learning (DL)Industrial internet of things
spellingShingle Zhang Yan
Piyush Kumar Shukla
Prashant Kumar Shukla
Kanika Thakur
Anurag Sinha
Saifullah Khalid
Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
International Journal of Computational Intelligence Systems
Cyber-physical systems
Industry 4.0
Intrusion detection and mitigation
Deep learning (DL)
Industrial internet of things
title Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
title_full Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
title_fullStr Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
title_full_unstemmed Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
title_short Intrusion Detection and Mitigation Method for the Industrial Internet of Things Using Bidirectional Convolutional Long Short-Term Memory and Deep Recurrent Convolutional Q-Networks
title_sort intrusion detection and mitigation method for the industrial internet of things using bidirectional convolutional long short term memory and deep recurrent convolutional q networks
topic Cyber-physical systems
Industry 4.0
Intrusion detection and mitigation
Deep learning (DL)
Industrial internet of things
url https://doi.org/10.1007/s44196-025-00890-9
work_keys_str_mv AT zhangyan intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks
AT piyushkumarshukla intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks
AT prashantkumarshukla intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks
AT kanikathakur intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks
AT anuragsinha intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks
AT saifullahkhalid intrusiondetectionandmitigationmethodfortheindustrialinternetofthingsusingbidirectionalconvolutionallongshorttermmemoryanddeeprecurrentconvolutionalqnetworks