Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems
Cyberattacks on power systems have doubled due to digitization, impacting healthcare, social, and economic sectors. False data injection attacks (FDIAs) are a significant threat, allowing attackers to manipulate power measurements and transfer malicious data to control centers. In this paper, we pro...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843273/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583985483481088 |
|---|---|
| author | Rachad Atat Abdulrahman Takiddin Muhammad Ismail Erchin Serpedin |
| author_facet | Rachad Atat Abdulrahman Takiddin Muhammad Ismail Erchin Serpedin |
| author_sort | Rachad Atat |
| collection | DOAJ |
| description | Cyberattacks on power systems have doubled due to digitization, impacting healthcare, social, and economic sectors. False data injection attacks (FDIAs) are a significant threat, allowing attackers to manipulate power measurements and transfer malicious data to control centers. In this paper, we propose the use of graphon neural networks (WNNs) for detecting various FDIAs. Unlike existing graph neural network (GNN)-based detectors, WNNs are efficient as they make use of the non-parametric graph processing method known as graphon, which is a limiting object of a sequence of dense graphs, whose family members share similar characteristics. This allows to leverage the learning by transference on the graphs to address the computational complexity and environmental concerns of training on large-scale systems, and the dynamicity resulting from the spatio-temporal evolution of power systems. Through experimental simulations, we show that WNN significantly improves FDIAs detection, training time, and real-time decision making under topological reconfigurations and growing system size with generalization and scalability benefits compared to conventional GNNs. |
| format | Article |
| id | doaj-art-7e730afe79ef43fb990df9ecdea512ea |
| institution | Kabale University |
| issn | 2687-7910 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Access Journal of Power and Energy |
| spelling | doaj-art-7e730afe79ef43fb990df9ecdea512ea2025-01-28T00:02:16ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102025-01-0112243510.1109/OAJPE.2025.353035210843273Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power SystemsRachad Atat0https://orcid.org/0000-0001-8075-6243Abdulrahman Takiddin1https://orcid.org/0000-0003-4793-003XMuhammad Ismail2https://orcid.org/0000-0002-8051-9747Erchin Serpedin3https://orcid.org/0000-0001-9069-770XDepartment of Computer Science and Mathematics, Lebanese American University, Beirut, LebanonDepartment of Electrical and Computer Engineering, FAMU-FSU College of Engineering, Florida State University, Tallahassee, FL, USACybersecurity Education, Research and Outreach Center (CEROC), Tennessee Technological University, Cookeville, TN, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USACyberattacks on power systems have doubled due to digitization, impacting healthcare, social, and economic sectors. False data injection attacks (FDIAs) are a significant threat, allowing attackers to manipulate power measurements and transfer malicious data to control centers. In this paper, we propose the use of graphon neural networks (WNNs) for detecting various FDIAs. Unlike existing graph neural network (GNN)-based detectors, WNNs are efficient as they make use of the non-parametric graph processing method known as graphon, which is a limiting object of a sequence of dense graphs, whose family members share similar characteristics. This allows to leverage the learning by transference on the graphs to address the computational complexity and environmental concerns of training on large-scale systems, and the dynamicity resulting from the spatio-temporal evolution of power systems. Through experimental simulations, we show that WNN significantly improves FDIAs detection, training time, and real-time decision making under topological reconfigurations and growing system size with generalization and scalability benefits compared to conventional GNNs.https://ieeexplore.ieee.org/document/10843273/Power gridsgraphon neural networksattacks detectiontransfer learningdynamic graphs |
| spellingShingle | Rachad Atat Abdulrahman Takiddin Muhammad Ismail Erchin Serpedin Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems IEEE Open Access Journal of Power and Energy Power grids graphon neural networks attacks detection transfer learning dynamic graphs |
| title | Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems |
| title_full | Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems |
| title_fullStr | Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems |
| title_full_unstemmed | Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems |
| title_short | Graphon Neural Networks-Based Detection of False Data Injection Attacks in Dynamic Spatio-Temporal Power Systems |
| title_sort | graphon neural networks based detection of false data injection attacks in dynamic spatio temporal power systems |
| topic | Power grids graphon neural networks attacks detection transfer learning dynamic graphs |
| url | https://ieeexplore.ieee.org/document/10843273/ |
| work_keys_str_mv | AT rachadatat graphonneuralnetworksbaseddetectionoffalsedatainjectionattacksindynamicspatiotemporalpowersystems AT abdulrahmantakiddin graphonneuralnetworksbaseddetectionoffalsedatainjectionattacksindynamicspatiotemporalpowersystems AT muhammadismail graphonneuralnetworksbaseddetectionoffalsedatainjectionattacksindynamicspatiotemporalpowersystems AT erchinserpedin graphonneuralnetworksbaseddetectionoffalsedatainjectionattacksindynamicspatiotemporalpowersystems |