AI-Enabled Cyber Risk Management and BCSI Security for NERC Critical Infrastructure Protection in the Bulk Electric System

Authors

  • Suchismita Chatterjee Cyber Security Product Specialist Expert Pacific Gas and Electric Company, USA Author

DOI:

https://doi.org/10.63503/aisem.69

Keywords:

Bulk Electric System, BCSI, NERC CIP, cyber-risk management, GNN, Transformer, digital twin, counterfactual AI, critical infrastructure

Abstract

Information technology (IT) converging with operational technology (OT), with SCADA and communication infrastructures, has greatly enriched the cyberattack surface for the Bulk Electric System (BES), making it easier for cyberattacks to occur against the BES Cyber Systems and BES Cyber System Information (BCSI). Existing AI-driven solutions are primarily centered around ID/Anomaly and limited by including BCSI exposure, cyber-physical dependencies, propagation of attack and NERC Critical Infrastructure Protection (CIP) requirements. The paper introduces a novel framework named CIP-SHIELD for cyber-risk management of BCSI-aware BES protection, based on artificial intelligence (AI). The framework incorporates a variety of elements, including a Cyber-Physical Security Twin, BCSI Digital Lineage Engine, Cyber Propagation Potential, hybrid GNN–Transformer risk prediction, counterfactual attack simulation and NERC-CIP reasoning. Evaluation against Random Forest, XGBoost, LSTM, Transformer, GNN and GNN-Transformer models demonstrates that CIP-SHIELD achieves an F1-score of 0.95, reduces the false-alert rate to 6.1% and detection latency to 3.6 s and obtains a risk prediction MAE of 0.041. Evaluation of cyber mitigation scenarios shows an average of 28.6% reduction in cyber risk projections as per counterfactual analysis. These findings prove the potential of CIP-SHIELD to combine BCSI exposure analysis, attack propagations prediction and risk quantification with the CIP-aware prevention decision support for CII.

References

[1] Sarker, I. H. (2024). AI for critical infrastructure protection and resilience. AI-driven cybersecurity and threat intelligence: Cyber automation, intelligent decision-making and explainability, 153-172. https://link.springer.com/chapter/10.1007/978-3-031-54497-2_9

[2] Achaal, B., Adda, M., Berger, M., Ibrahim, H., & Awde, A. (2024). Study of smart grid cyber-security, examining architectures, communication networks, cyber-attacks, countermeasure techniques and challenges. Cybersecurity, 7(1), 10. https://link.springer.com/article/10.1186/s42400-023-00200-w

[3] Agarwal, L., Jaint, B., & Mandpura, A. K. (2024). Reducing overfitting in deep learning intrusion detection for power systems with CTGAN. Chaos, Solitons & Fractals, 188, 115603. https://doi.org/10.1016/j.chaos.2024.115603

[4] Bitirgen, K., & Filik, Ü. B. (2023). A hybrid deep learning model for discrimination of physical disturbance and cyber-attack detection in smart grid. International Journal of Critical Infrastructure Protection, 40, 100582. https://doi.org/10.1016/j.ijcip.2022.100582

[5] Ahmed, M., & Pathan, A. S. K. (2020). False data injection attack (FDIA): an overview and new metrics for fair evaluation of its countermeasure. Complex Adaptive Systems Modeling, 8(1), 4. https://link.springer.com/article/10.1186/s40294-020-00070-w

[6] Das, T. K., Adepu, S., & Zhou, J. (2020). Anomaly detection in industrial control systems using logical analysis of data. Computers & Security, 96, 101935. https://doi.org/10.1016/j.cose.2020.101935

[7] Mehrdad, S., Mousavian, S., Madraki, G., & Dvorkin, Y. (2018). Cyber-physical resilience of electrical power systems against malicious attacks: A review. Current Sustainable/Renewable Energy Reports, 5(1), 14-22. https://link.springer.com/article/10.1007/s40518-018-0094-8

[8] Almalawi, A., Yu, X., Tari, Z., Fahad, A., & Khalil, I. (2014). An unsupervised anomaly-based detection approach for integrity attacks on SCADA systems. Computers & Security, 46, 94-110. https://doi.org/10.1016/j.cose.2014.07.005

[9] Palleti, V. R., Adepu, S., Mishra, V. K., & Mathur, A. (2021). Cascading effects of cyber-attacks on interconnected critical infrastructure. Cybersecurity, 4(1), 8. https://link.springer.com/article/10.1186/s42400-021-00071-z

[10] Podapati, V. H., Nigam, D., & Das, S. (2025, July). SoK: a systematic review of context-and behavior-aware adaptive authentication in mobile environments. In International Symposium on Human Aspects of Information Security and Assurance (pp. 406-419). Cham: Springer Nature Switzerland. https://link.springer.com/chapter/10.1007/978-3-032-02504-3_28

[11] Hamdi, N. (2025). Enhancing Cybersecurity in smart grid: a review of machine learning approaches: Najet Hamdi. Telecommunication Systems, 88(2), 72. https://link.springer.com/article/10.1007/s11235-025-01308-9

[12] Alsirhani, A., Tariq, N., Humayun, M., Naif Alwakid, G., & Sanaullah, H. (2025). Intrusion detection in smart grids using artificial intelligence-based ensemble modelling. Cluster Computing, 28(4), 238. https://link.springer.com/article/10.1007/s10586-024-04964-9

[13] Li, Y., & Wu, J. (2022). Low latency cyberattack detection in smart grids with deep reinforcement learning. International Journal of Electrical Power & Energy Systems, 142, 108265. https://doi.org/10.1016/j.ijepes.2022.108265

[14] Alani, M. M., Mauri, L., & Damiani, E. (2023). A two-stage cyber attack detection and classification system for smart grids. Internet of Things, 24, 100926. https://doi.org/10.1016/j.iot.2023.100926

[15] Xie, R., Wang, B., & Xu, X. (2025). A novel federated deep learning for intrusion detection in smart grid cyber-physical systems. Engineering Applications of Artificial Intelligence, 162, 112404. https://doi.org/10.1016/j.engappai.2025.112404

[16] Afrin, S., Al weMuttaki, M. R., Anil, A. I. A., & Hasan, S. (2025). AI-powered cybersecurity for smart grid communication: A systematic review of intrusion detection and threat mitigation systems. Energy Conversion and Management: X, 101416. https://doi.org/10.1016/j.ecmx.2025.101416

[17] Hotellier, E., Sicard, F., Francq, J., & Mocanu, S. (2024). Standard specification-based intrusion detection for hierarchical industrial control systems. Information Sciences, 659, 120102. https://doi.org/10.1016/j.ins.2024.120102

[18] Mukherjee, D., Chakraborty, S., & Ghosh, S. (2022). Deep learning-based multilabel classification for locational detection of false data injection attack in smart grids. Electrical Engineering, 104(1), 259-282. https://link.springer.com/article/10.1007/s00202-021-01278-6

[19] Jeyasoundari, J., Sridevi, S., Charles Raja, S. S., & Karthick, T. (2026). Edge-based man-in-the-middle attack detection in advanced metering infrastructure using a hybrid CNN–GRU–LSTM model. Sādhanā, 51(3), 218. https://link.springer.com/article/10.1007/s12046-026-03230-5

[20] Francia III, G. A., & El-Sheikh, E. (2022). NERC CIP standards: Review, compliance and training. Global Perspectives on Information Security Regulations: Compliance, Controls and Assurance, 48-71. DOI: 10.4018/978-1-7998-8390-6.ch003

[21] Guarino, A. (2015, October). Information security standards in critical infrastructure protection. In ISSE 2015: Highlights of the Information Security Solutions Europe 2015 Conference (pp. 263-269). Wiesbaden: Springer Fachmedien Wiesbaden. https://link.springer.com/chapter/10.1007/978-3-658-10934-9_22

[22] El Mrabet, Z., Kaabouch, N., El Ghazi, H., & El Ghazi, H. (2018). Cyber-security in smart grid: Survey and challenges. Computers & Electrical Engineering, 67, 469-482. https://doi.org/10.1016/j.compeleceng.2018.01.015

[23] Efatinasab, E., Azadi, N., Susto, G. A., Ahmed, C. M., & Rampazzo, M. (2025). Fortifying smart grid stability: Defending against adversarial attacks and measurement anomalies. Sustainable Energy, Grids and Networks, 43, 101799. https://doi.org/10.1016/j.segan.2025.101799

[24] Achaal, B., Adda, M., Berger, M., Ibrahim, H., & Awde, A. (2024). Study of smart grid cyber-security, examining architectures, communication networks, cyber-attacks, countermeasure techniques and challenges. Cybersecurity, 7(1), 10. https://link.springer.com/article/10.1186/s42400-023-00200-w

[25] Adewusi, M. A., & Mustafa, M. M. (2026). Machine learning for power-grid cybersecurity: a review. Discover Computing, 29(1), 282. https://link.springer.com/article/10.1007/s10791-026-10162-5

[26] http://www.kaggle.com/datasets/cicdataset/cicids2017

[27] http://www.kaggle.com/datasets/mrwellsdavid/unsw-nb15

[28] http://www.kaggle.com/datasets/dhoogla/csecicids2018

Published

2026-10-24