SVC and Bi-LSTM with XGBoost Classifier -Based Radio Frequency Fingerprint Identification in Smart Grid Security

Abstract

The Smart Grid (SG), a sophisticated electrical network that uses digital technology to monitor and regulate power flow, is susceptible to cyberattacks like eavesdropping, data spoofing, and data falsification. Although there are cryptographic solutions, managing certificate revocation lists (CRLs) is still difficult, and public-key cryptography (PKC) is sometimes unfeasible for inexpensive, power-constrained IoT devices. By taking advantage of hardware flaws in RF devices, Radio Frequency Fingerprint Identification (RFFI) has become a viable non-cryptographic security method. However, for practical implementation, strong deep-learning architectures and efficient deep signal preprocessing are needed. For the first time, we combine XGBoost and BiLSTM in this study to present a hybrid classification framework for RFFI. The accuracy of a Support Vector Classifier (SVC) trained on 15,000 data was 92.6%, whereas the BiLSTM-XGBoost model obtained 97.5% accuracy on 5,000 samples. Furthermore, 97% accuracy was obtained when XGBoost was applied to channel-estimated and equalized wireless data. These findings show how well hybrid deep learning techniques work to strengthen Smart Grid security against online attacks.

Keywords

• Smart Grid (SG)
• Cyber Attack
• Radio Frequency Fingerprint Identification (RFFI)
• Carrier Frequency Offset (CFO)
• Bidirectional LSTM

References

1. [1] Vineeth, V. V., Radhikab, N., Vanithaa, V., “Intruder detection and prevention in a smart grid communication system”, Smart Grid Technologies, India Procedia Technology 21, Coimbatore-641112, 393–399, (2015). DOI: https://doi.org/10.1016/j.protcy.2015.10.058
2. [2] Xia, J., Wang, Y., “Secure key distribution for the smart grid”. IEEE Transactions on Smart Grid, 3(3): 1437-1443, (2012). DOI: https://doi.org/10.1109/TSG.2012.2199141
3. [3] Gunduz, M. Z., Das, R.,” Analysis of cyber-attacks on smart grid applications”, IEEE Xplore, 1-5, (2018). DOI: https://doi.org/10.1109/IDAP.2018.8620728
4. [4] Bou-Harb, E., Fachkha, C., Pourzandi, M., Debbabi, M., Assi, C., “Communication security for smart grid distribution networks”, IEEE Communications Magazine, 42-49, (2013).
5. [5] Wang, W., Lu, Z., “Cyber security in the smart grid: survey and challenges”, Computer Networks 57: 1344–1371, (2013). DOI: https://doi.org/10.1109/MCOM.2013.6400437
6. [6] Abla, S., Khelifa, B., “Security concerns in smart grids: threats, vulnerabilities and countermeasures”, IEEE Xplore, 1-6, (2015). DOI: https://doi.org/ 10.1109/IRSEC.2015.7454963
7. [7] Shen, G., Zhang, J., Marshall, A., Cavallaro, J., IEEE, “Towards scalable and channel-robust radio frequency fingerprint identification for LoRa” IEEE, 1-12, (2021). DOI: https://doi.org/10.1109/TIFS.2022.3152404
8. [8] He, D., Chan, S., Zhang, Y., Guizani, M., Chen, C. Bu, J. “An enhanced public key ınfrastructure to secure smart grid wireless communication networks”., IEEE Network, 10-16, (2014). DOI: https://doi.org/10.1109/MNET.2014.6724101

9. [9] Shen, G., Zhang, J., Marshall, A., Cavallaro, J. R., “Towards scalable and channel-robust radio frequency fingerprint identification for LoRa,” IEEE Transactions on Information Forensics and Security, 17: 774–787, (2022). DOI: https://doi.org/ 10.1109/TIFS.2022.3152404
10. [10] Tang, C., Yan, T., An, Y., “Radio frequency fingerprint recognition based on deep learning,” In 2021 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), 708-711, (2021). DOI: https://doi.org/ 10.1109/ICITBS53129.2021.00177
11. [11] Merchant, K., Revay, S., Stantchev, G., Nousain, B., “Deep learning for rf device fingerprinting in cognitive communication networks,” IEEE Journal of Selected Topics in Signal Processing, 12(1): 160–167, (2018). DOI: https://doi.org/ 10.1109/JSTSP.2018.2796446
12. [12] Shiri, F. M., Perumal, Mustapha, N., Mohamed, R., “A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU”. ArXiv Preprint ArXiv:2305.17473, 1-16, (2023). DOI: 10.48550/arXiv.2305.17473
13. [13] Saini, R., Verma, Y. P., Saluja, K. K., “Machine learning classifier-based detection of cyber-attack on power system: Comparative analysis,” IEEE, 22nd National Power Systems Conference, 465-470, (2022). DOI: https://doi.org/ 10.1109/NPSC57038.2022.10069603
14. [14] Shen, G., Zhang, J., Marshall, A., Cavallaro, J. R., “Towards scalable and channel-robust radio frequency fingerprint identification for LoRa,” IEEE Transactions on Information Forensics and Security, 17: 774–787, (2022). DOI: https://doi.org/10.1109/TIFS.2022.3152404
15. [15] Shen, G., Zhang, J., Marshall, A., “Deep learning - powered radio frequency fingerprint identification: methodology and case study,” IEEE Communications Magazine, 61(9): 170–176, (2023). DOI: https://doi.org/10.1109/MCOM.001.2200695
16. [16] Synchronization Signals (PSS and SSS) - MATLAB & Simulink.” https://www.mathworks.com/help/lte/ug/synchro nization-signals-pss-and-sss.html
17. [17] Shen, G., Zhang, J., Marshall, A., Peng, L. Wang, X., “Radio frequency fingerprint identification for lora using deep learning,” IEEE Journal on Selected Areas in Communications, 39(8): 2604–2616, (2021). DOI: https://doi.org/10.1109/JSAC.2021.3087250
18. [18] Shen, G., Zhang, J., Marshall, A., Peng, L., Wang, X., “Radio frequency fingerprint identification for LoRa using spectrogram and CNN,” IEEE 2021-IEEE Conference on Computer Communications, 1-10, (2021). DOI: https://doi.org/10.1109/INFOCOM42981.2021.9488793
19. [19] Zaier, N. A., and Bouallegue, R. “Channel Estimation Study for Block - Pilot Insertion in OFDM Systems Under Slowly Time Varying Conditions,” International Journal of Computer Networks & Communications, 6(3): 39–54, (2011). DOI: https://doi.org/10.5121/ijcnc.2011.3603
20. [20] Khan, A. M., Jeoti, V., and Zakariya, M. A., “Improved pilot-based LS and MMSE channel estimation using DFT for DVB-T OFDM systems,” IEEE Symposium on Wireless Technology & Applications (ISWTA), 3, 120-124, (2013). DOI: https://doi.org/ 10.1109/iswta.2013.6688752
21. [21] Assaf, A., Kandil, N., Hakem, N., Affes, S. and Fortier, P.,“A study of 60 GHz channel estimation techniques using pilot carriers in OFDM systems in a confined area,” IEEE International Conference on Wireless Communications in Underground and Confined Areas, 1-6, (2012). DOI: https://doi.org/ 10.1109/icwcuca.2012.6402505
22. [22] Kewen, L., and Ke, X., “Research of MMSE and LS channel estimation in OFDM systems,” IEEE International Conference On Information Science And Engineering, 2308-2311, (2010). DOI: https://doi.org/10.1109/icise.2010.5688562
23. [23] Mohammed, I. A., “Analysis and performance evaluation of SISO and MIMO OFDM channel estimation techniques using pilot symbols,” (2015). [Online]. Available: https://commons.lib.niu.edu/handle/10843/18858
24. [24] Awan, M. A., Dalveren, Y., Catak, F. O., and Kara, A., “Deployment and implementation aspects of radio frequency fingerprinting in cybersecurity of smart grids,” Electronics, 24(12): 4914, (2023). DOI: https://doi.org/10.3390/electronics12244914
25. [25] Iyiparlakoglu, R., Awan M., A., Dalveren Y, and Kara A., "Optimizing Radio Frequency Fingerprinting for Device Classification: A Study Towards Lightweight DL Models," The 6th International Conference on Communications, Signal Processing, and their Applications, Türkiye, (2024). DOI: https://doi.org/10.1109/ICCSPA61559.2024.10794386