A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems
The emergence of cyber-physical smart grid (CPSG) systems has revolutionized the traditional power grid by enabling the bidirectional energy flow between consumers and utilities. However, due to escalated information exchange between the end-users, it has posed a greater challenge to the cyber secur...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10050022/ |
| _version_ | 1811161972555644928 |
|---|---|
| author | Devinder Kaur Adnan Anwar Innocent Kamwa Shama Islam S. M. Muyeen Nasser Hosseinzadeh |
| author_facet | Devinder Kaur Adnan Anwar Innocent Kamwa Shama Islam S. M. Muyeen Nasser Hosseinzadeh |
| author_sort | Devinder Kaur |
| collection | DOAJ |
| description | The emergence of cyber-physical smart grid (CPSG) systems has revolutionized the traditional power grid by enabling the bidirectional energy flow between consumers and utilities. However, due to escalated information exchange between the end-users, it has posed a greater challenge to the cyber security mechanisms for the communication networks at the cyber and physical planes. To address these challenges, we propose a Bayesian approach integrated with deep convolutional neural networks (CNN-Bayesian). While, the Bayesian component is used to discriminate cyber-physical intrusions from the normal events in the binary and multi-class events. CNN layers are utilized to handle the high-dimensional feature space prior to the intrusions classification task. The proposed method is validated using real-time Industrial control systems (ICS) dataset against the standard deep learning-based classification methods such as recurrent neural networks (RNN) and long-short term memory (LSTM). From the experimental results, it can be inferred that the proposed CNN-Bayesian method outperforms the existing benchmark classification methods to discriminate intrusions in CPSG systems using evaluation metrics such as accuracy, precision, recall, and <inline-formula> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula>-score. |
| first_indexed | 2024-04-10T06:22:29Z |
| format | Article |
| id | doaj.art-29375062c86a46ee8d3b16c205acf85e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:22:29Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-29375062c86a46ee8d3b16c205acf85e2023-03-02T00:00:48ZengIEEEIEEE Access2169-35362023-01-0111189101892010.1109/ACCESS.2023.324794710050022A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid SystemsDevinder Kaur0Adnan Anwar1https://orcid.org/0000-0003-0070-182XInnocent Kamwa2https://orcid.org/0000-0002-3568-3716Shama Islam3https://orcid.org/0000-0002-2354-7960S. M. Muyeen4https://orcid.org/0000-0003-4955-6889Nasser Hosseinzadeh5https://orcid.org/0000-0002-8755-1176School of Engineering, Deakin University, Geelong, VIC, AustraliaCentre for Cyber Security Research and Innovation (CSRI), School of Information Technology, Deakin University, Geelong, VIC, AustraliaDepartment of Electrical Engineering and Computer Engineering, Laval University, Quebec City, CanadaSchool of Engineering, Deakin University, Geelong, VIC, AustraliaDepartment of Electrical Engineering, Qatar University, Doha, QatarSchool of Engineering, Deakin University, Geelong, VIC, AustraliaThe emergence of cyber-physical smart grid (CPSG) systems has revolutionized the traditional power grid by enabling the bidirectional energy flow between consumers and utilities. However, due to escalated information exchange between the end-users, it has posed a greater challenge to the cyber security mechanisms for the communication networks at the cyber and physical planes. To address these challenges, we propose a Bayesian approach integrated with deep convolutional neural networks (CNN-Bayesian). While, the Bayesian component is used to discriminate cyber-physical intrusions from the normal events in the binary and multi-class events. CNN layers are utilized to handle the high-dimensional feature space prior to the intrusions classification task. The proposed method is validated using real-time Industrial control systems (ICS) dataset against the standard deep learning-based classification methods such as recurrent neural networks (RNN) and long-short term memory (LSTM). From the experimental results, it can be inferred that the proposed CNN-Bayesian method outperforms the existing benchmark classification methods to discriminate intrusions in CPSG systems using evaluation metrics such as accuracy, precision, recall, and <inline-formula> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula>-score.https://ieeexplore.ieee.org/document/10050022/Bayesian inferencecybersecuritydeep learningintrusion-detection systemsSCADAsmart grid |
| spellingShingle | Devinder Kaur Adnan Anwar Innocent Kamwa Shama Islam S. M. Muyeen Nasser Hosseinzadeh A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems IEEE Access Bayesian inference cybersecurity deep learning intrusion-detection systems SCADA smart grid |
| title | A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems |
| title_full | A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems |
| title_fullStr | A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems |
| title_full_unstemmed | A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems |
| title_short | A Bayesian Deep Learning Approach With Convolutional Feature Engineering to Discriminate Cyber-Physical Intrusions in Smart Grid Systems |
| title_sort | bayesian deep learning approach with convolutional feature engineering to discriminate cyber physical intrusions in smart grid systems |
| topic | Bayesian inference cybersecurity deep learning intrusion-detection systems SCADA smart grid |
| url | https://ieeexplore.ieee.org/document/10050022/ |
| work_keys_str_mv | AT devinderkaur abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT adnananwar abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT innocentkamwa abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT shamaislam abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT smmuyeen abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT nasserhosseinzadeh abayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT devinderkaur bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT adnananwar bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT innocentkamwa bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT shamaislam bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT smmuyeen bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems AT nasserhosseinzadeh bayesiandeeplearningapproachwithconvolutionalfeatureengineeringtodiscriminatecyberphysicalintrusionsinsmartgridsystems |