PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems
Smart grids are vulnerable to stealthy false data injection attacks (SFDIAs), as SFDIAs can bypass residual-based bad data detection mechanisms. Methods based on deep learning technology have shown promising accuracy in the detection of SFDIAs. However, most existing methods rely on the temporal str...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of the Computer Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9861714/ |
| _version_ | 1811274690383052800 |
|---|---|
| author | Xuefei Yin Yanming Zhu Yi Xie Jiankun Hu |
| author_facet | Xuefei Yin Yanming Zhu Yi Xie Jiankun Hu |
| author_sort | Xuefei Yin |
| collection | DOAJ |
| description | Smart grids are vulnerable to stealthy false data injection attacks (SFDIAs), as SFDIAs can bypass residual-based bad data detection mechanisms. Methods based on deep learning technology have shown promising accuracy in the detection of SFDIAs. However, most existing methods rely on the temporal structure of a sequence of measurements but do not take account of the spatial structure between buses and transmission lines. To address this issue, we propose a spatiotemporal deep network, PowerFDNet, for the SFDIA detection in AC-model power grids. The PowerFDNet consists of two sub-architectures: spatial architecture (SA) and temporal architecture (TA). The SA is aimed at extracting representations of bus/line measurements and modeling the spatial structure based on their representations. The TA is aimed at modeling the temporal structure of a sequence of measurements. Therefore, the proposed PowerFDNet can effectively model the spatiotemporal structure of measurements. Case studies on the detection of SFDIAs on the benchmark smart grids show that the PowerFDNet achieved significant improvement compared with the state-of-the-art SFDIA detection methods. In addition, an IoT-oriented lightweight prototype of size 52 MB is implemented and tested for mobile devices, which demonstrates the potential applications on mobile devices. The trained model will be available at [Online]. Available: <uri>https://github.com/FrankYinXF/PowerFDNet</uri>. |
| first_indexed | 2024-04-12T23:24:32Z |
| format | Article |
| id | doaj.art-37aff37c307a467d8d670a49b65d9127 |
| institution | Directory Open Access Journal |
| issn | 2644-1268 |
| language | English |
| last_indexed | 2024-04-12T23:24:32Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Computer Society |
| spelling | doaj.art-37aff37c307a467d8d670a49b65d91272022-12-22T03:12:27ZengIEEEIEEE Open Journal of the Computer Society2644-12682022-01-01314916110.1109/OJCS.2022.31997559861714PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission SystemsXuefei Yin0https://orcid.org/0000-0002-5784-7419Yanming Zhu1https://orcid.org/0000-0002-8238-8090Yi Xie2https://orcid.org/0000-0002-8899-4032Jiankun Hu3https://orcid.org/0000-0003-0230-1432School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, AustraliaSchool of Computer Science and Engineering, University of New South Wales, Sydney, NSW, AustraliaSchool of Data and Computer Science (and the GuangDong Province Key Laboratory of Information Security Technology), Sun Yat-sen University, Guangzhou, ChinaSchool of Engineering and Information Technology, University of New South Wales, Canberra, ACT, AustraliaSmart grids are vulnerable to stealthy false data injection attacks (SFDIAs), as SFDIAs can bypass residual-based bad data detection mechanisms. Methods based on deep learning technology have shown promising accuracy in the detection of SFDIAs. However, most existing methods rely on the temporal structure of a sequence of measurements but do not take account of the spatial structure between buses and transmission lines. To address this issue, we propose a spatiotemporal deep network, PowerFDNet, for the SFDIA detection in AC-model power grids. The PowerFDNet consists of two sub-architectures: spatial architecture (SA) and temporal architecture (TA). The SA is aimed at extracting representations of bus/line measurements and modeling the spatial structure based on their representations. The TA is aimed at modeling the temporal structure of a sequence of measurements. Therefore, the proposed PowerFDNet can effectively model the spatiotemporal structure of measurements. Case studies on the detection of SFDIAs on the benchmark smart grids show that the PowerFDNet achieved significant improvement compared with the state-of-the-art SFDIA detection methods. In addition, an IoT-oriented lightweight prototype of size 52 MB is implemented and tested for mobile devices, which demonstrates the potential applications on mobile devices. The trained model will be available at [Online]. Available: <uri>https://github.com/FrankYinXF/PowerFDNet</uri>.https://ieeexplore.ieee.org/document/9861714/Stealthy false data injection attack (SFDIA) detectionbad data detectionspatiotemporal deep learning network |
| spellingShingle | Xuefei Yin Yanming Zhu Yi Xie Jiankun Hu PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems IEEE Open Journal of the Computer Society Stealthy false data injection attack (SFDIA) detection bad data detection spatiotemporal deep learning network |
| title | PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems |
| title_full | PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems |
| title_fullStr | PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems |
| title_full_unstemmed | PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems |
| title_short | PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-Model Transmission Systems |
| title_sort | powerfdnet deep learning based stealthy false data injection attack detection for ac model transmission systems |
| topic | Stealthy false data injection attack (SFDIA) detection bad data detection spatiotemporal deep learning network |
| url | https://ieeexplore.ieee.org/document/9861714/ |
| work_keys_str_mv | AT xuefeiyin powerfdnetdeeplearningbasedstealthyfalsedatainjectionattackdetectionforacmodeltransmissionsystems AT yanmingzhu powerfdnetdeeplearningbasedstealthyfalsedatainjectionattackdetectionforacmodeltransmissionsystems AT yixie powerfdnetdeeplearningbasedstealthyfalsedatainjectionattackdetectionforacmodeltransmissionsystems AT jiankunhu powerfdnetdeeplearningbasedstealthyfalsedatainjectionattackdetectionforacmodeltransmissionsystems |