Detection of False Data Injection Attacks: A Protected Federated Deep Learning Based on Encryption Mechanism
Source abstract
Abstract
False Data Injection Attack (FDIA), a disruptive cyber threat, is becoming increasingly detrimental to smart grids with the deepening integration of information technology and physical power systems, leading to system unreliability, data integrity loss and operational vulnerability exposure. Given its widespread harm and impact, conducting in-depth research on FDIA detection is vitally important. This paper innovatively introduces a FDIA detection scheme: A Protected Federated Deep Learning (ProFed), which leverages Federated Averaging algorithm (FedAvg) as a foundational framework to fortify data security, harnesses pre-trained enhanced spatial-temporal graph neural networks (STGNN) to perform localized model training and integrates the Cheon-Kim-Kim-Song (CKKS) homomorphic encryption system to secure sensitive information. Simulation tests on IEEE 14-bus and IEEE 118-bus systems demonstrate that our proposed method outperforms other state-of-the-art detection methods across all evaluation metrics, with peak improvements reaching up to 35%.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Internet Traffic Analysis and Secure E-voting · Privacy-Preserving Technologies in Data · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (51)
Show source-provided references
1. Smart grid technologies: communication technologies and standards10.1109/TII.2011.2166794 ↗
2. Ekanayake · Smart grid: technology and applications · 201210.1002/9781119968696 ↗
3. Smart grids: a cyber–physical systems perspective10.1109/JPROC.2015.2503119 ↗
4. Federated learning under attack: exposing vulnerabilities through data poisoning attacks in computer networks10.1109/TNSM.2025.3525554 ↗
5. Unknown web attack threat detection based on large language model10.1016/j.asoc.2025.112905 ↗
6. False data injection attacks against state estimation in electric power grids
7. Analysis of the cyber attack on the Ukrainian power grid
8. Limiting false data attacks on power system state estimation
9. Detection and isolation of false data injection attack for smart grids via unknown input observers10.1049/iet-gtd.2018.5139 ↗
10. Detection of false data injection attacks on smart grids: A resilience–enhanced scheme10.1109/TPWRS.2021.3127353 ↗
11. Detecting false data injection attacks in smart grids: a semi-supervised deep learning approach10.1109/TSG.2020.3010510 ↗
12. Distributed state estimation of active distribution networks considering false data injection attacks
13. Distributed detection method for a false data attack in a power grid based on edge computing
14. Graph neural networks based detection of stealth false data injection attacks in smart grids10.1109/JSYST.2021.3109082 ↗
15. Distributed unsupervised detection for robust power system false data attacks via flexible dynamic time warping strategy10.1109/TII.2024.3452202 ↗
16. Pre-training enhanced spatial-temporal graph neural network for multivariate time series forecasting
17. Detection of false data injection attacks in smart grid: a secure federated deep learning approach10.1109/TSG.2022.3204796 ↗
18. False data injection on state estimation in power systems—Attacks, impacts, and defense: a survey10.1109/TII.2016.2614396 ↗
19. Propensity Weighted federated learning for treatment effect estimation in distributed imbalanced environments10.1016/j.compbiomed.2024.108779 ↗
20. Xia Y, Yang D, Li W, Myronenko A, Xu D, Obinata H, et al. Auto-FedAvg: learnable federated averaging for multi-institutional medical image segmentation. arXiv preprint. 2021. doi:10.48550/arXiv.2104.10195.
21. A federated machine learning approach for order-level risk prediction in supply chain financing10.1016/j.ijpe.2023.109095 ↗
22. AFedAvg: communication-efficient federated learning aggregation with adaptive communication frequency and gradient sparse10.1080/0952813X.2022.2079730 ↗
23. Federated learning-based cross-enterprise recommendation with graph neural networks10.1109/TII.2022.3203395 ↗
24. Privacy-preserving federated learning for detecting false data injection attacks on power system10.1016/j.epsr.2024.110150 ↗
25. An efficient privacy-enhancing cross-silo federated learning and applications for false data injection attack detection in smart grids10.1109/TIFS.2023.3267892 ↗
26. Bottou · Neural networks: tricks of the trade · 2012 · 421
27. Huang · Applied time series analysis and forecasting with python · 2022 · 21510.1007/978-3-031-13584-2_7 ↗
28. Spatial-temporal transformer networks for traffic flow forecasting using a pre-trained language model10.3390/s24175502 ↗
29. STGNN-FAM: a traffic flow prediction model for spatiotemporal graph networks based on fusion of attention mechanisms10.1155/2023/8880530 ↗
30. Pan · Urban intersection traffic flow prediction: a physics-guided stepwise framework utilizing spatio-temporal graph neural network algorithms · 2025 · 4 · 100207
31. An interval forecast model for infectious diseases using fuzzy information granulation and spatial-temporal graph neural network
32. An artificial intelligent-based model for detecting systolic pathological patterns of phonocardiogram based on time-growing neural network10.1016/j.asoc.2019.105615 ↗
33. Multi-area short-term load forecasting based on spatiotemporal graph neural network10.1016/j.engappai.2024.109398 ↗
34. A multi-scale spatial-temporal graph neural network-based method of multienergy load forecasting in integrated energy system10.1109/TSG.2023.3315750 ↗
35. Stealth FDIA localization in power systems using spatio-temporal graph neural networks
36. Application layer DDoS detection method based on spatio-temporal graph neural network
37. A GNN-based false data detection scheme for smart grids10.3390/a18030166 ↗
38. Cheon · Advances in Cryptology-ASIACRYPT 2017: 23rd International Conference on the Theory and Applications of Cryptology and Information Security · 2017 · 40910.1007/978-3-319-70694-8_15 ↗
39. Wu · Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data · 2024 · 199
40. Privacy-preserving rule induction using CKKS10.1109/ACCESS.2024.3498040 ↗
41. EvalComp: bootstrapping based on homomorphic comparison function for CKKS10.1109/TIFS.2024.3516553 ↗
42. A secure data fitting scheme based on CKKS homomorphic encryption for medical IoT10.3233/JHS-222016 ↗
43. Privacy-preserving machine learning with fully homomorphic encryption for deep neural network10.1109/ACCESS.2022.3159694 ↗
44. Secure speech retrieval method using deep hashing and CKKS fully homomorphic encryption10.1007/s11042-024-18113-2 ↗
45. A privacy-preserving federated reinforcement learning method for multiple virtual power plants scheduling[J]10.1109/TCSI.2024.3479427 ↗
46. Fathony RZA. Performance-aligned learning algorithms with statistical guarantees. Chicago: University of Illinois; 2019. [cited 2025 Apr 15]. Available from: https://www.proquest.com/docview/2342583943?sourcetype=Dissertations%20&%20Theses.
47. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not10.5194/gmd-15-5481-2022 ↗
48. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions10.1186/s40537-021-00444-8 ↗
49. A review of recurrent neural networks: LSTM cells and network architectures10.1162/neco_a_01199 ↗
50. Taheri · International Conference on Information and Knowledge Systems · 2024 · 168
51. FedSHE: privacy preserving and efficient federated learning with adaptive segmented CKKS homomorphic encryption10.1186/s42400-024-00232-w ↗