Comparative Analysis of Threat Detection Model Adaptation Strategies Using a Digital Twin in Critical Information Infrastructure Objects
( Pp. 159-166)

Building on the previously developed method for adaptive threat detection and a software prototype of a digital twin for automated power grid control systems, this paper presents a comparative analysis of three strategies for maintaining the relevance of information security threat detection models for critical information infrastructure (CII) objects. The approach is validated using the example of an automated control system for an intelligent power grid. The examined strategies include: a static strategy (without model updates), a strategy of retraining on real data, and an adaptation strategy using a digital twin, where model updates are based on synthetic data generated in a virtual environment. Experimental evaluation was conducted on a simulation platform that reproduces telemetry and typical operating modes, as well as models of cyberattacks: imitation of normal changes, pulse attacks, and combined attacks. The results demonstrate that the static model is incapable of detecting new types of threats, while both adaptive strategies provide high detection recall. The strategy employing a digital twin achieves the highest recall with a comparable level of false positives, while simultaneously minimizing the use of data from the real object and reducing operational risks.

Mityakov E.S. Comparative analysis of threat detection model adaptation strategies using a digital twin in critical information infrastructure objects. Computational Nanotechnology. 13, 1 (2026), 159–166. DOI: 10.33693/2313-223X-2026-13-1-159-166. EDN: MTBBKG

Mityakov E.S. Method for Detecting Indicators of Information Security Threats to Critical Information Infrastructure Objects Based on Digital Twins. Computational Nanotechnology. 2025. Vol. 12. No. 3. Pp. 115–122. (In Rus.). DOI: 10.33693/2313-223X-2025-12-3-115-122. EDN: BGUXHV
Mityakov E.S. Development of a digital twin prototype for an automated smart grid control system for cybersecurity threat analysis. Computational Nanotechnology. 2025. Vol. 12. No. 4. Pp. 116–123. (In Rus.). DOI: 10.33693/2313-223X-2025-12-4-116-123. EDN: FYAFEH
Erkek İ., Irmak E. Enhancing cybersecurity of a hydroelectric power plant through digital twin modeling and explainable AI. IEEE Access. 2025. Vol. 13. Pp. 41887–41908. DOI: 10.1109/ACCESS.2025.3547672.
Gehrmann C., Gunnarsson M. A digital twin based industrial automation and control system security architecture. IEEE Transactions on Industrial Informatics. 2020. Vol. 16. Pp. 669–680. DOI: 10.1109/TII.2019.2938885.
Hammar K., Stadler R. Digital twins for security automation. In: NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium. 2023. Pp. 1–6. DOI: 10.1109/NOMS56928.2023.10154288.
Homaei M., Mogollon-Gutierrez O., Sancho J., Ávila M., Caro A. A review of digital twins and their application in cybersecurity based on artificial intelligence. Artificial Intelligence Review. 2024. Vol. 57. Art. 201. DOI: 10.1007/s10462-024-10805-3.
Jeremiah S.R., Azzaoui A., Xiong N., Park J. A compre­hensive survey of digital twins: Applications, techno­logies and security challenges. Journal of Systems Architecture. 2024. Vol. 151. Art. 103120. DOI: 10.1016/j.sysarc.2024.103120.
Krishnaveni S., Chen T., Sathiyanarayanan M., Amutha B. CyberDefender: An integrated intelligent defense framework for digital-twin-based industrial cyber-physical systems. Cluster Computing. 2024. Vol. 27. Pp. 7273–7306. DOI: 10.1007/s10586-024-04320-x.
Mityakov E., Ladynin A., Shmeleva A., Kazakevich I. Critical information infrastructures intelligent protection: Digital twins and neural network-based threat detection methods. In: VI International Conference on Neural Networks and Neurotechnologies (NeuroNT). 2025. Pp. 22–25. DOI: 10.1109/neuront66873.2025.11049978.
Praveenkumar K., Balasm Z., Bharathi P. et al. Digital twins driven by artificial intelligence to mitigate, detect, and simulate virtual space cyber threats. In: International Conference on Computational Innovations and Engineering Sustainability (ICCIES). 2025. Pp. 1–6. DOI: 10.1109/iccies63851.2025.11032312.
Salim M., Camacho D., Park J. Digital twin and federated learning enabled cyberthreat detection system for IoT networks. Future Generation Computer Systems. 2024. Vol. 161. Pp. 701–713. DOI: 10.1016/j.future.2024.07.017.
Sen Ö., Bleser N., Ulbig A. Digital twin for evaluating detective countermeasures in smart grid cybersecurity. In: IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm). 2023. Pp. 1–6. DOI: 10.1109/SmartGridComm57358.2023.10333871.
Shan A., Myeong S. Proactive threat hunting in critical infrastructure protection through hybrid machine learning algorithm application. Sensors. 2024. Vol. 24. Art. 4888. DOI: 10.3390/s24154888.
Sousa B., Arieiro M., Pereira V. et al. ELEGANT: Security of critical infrastructures with digital twins. IEEE Access. 2021. Vol. 9. Pp. 107574–107588. DOI: 10.1109/ACCESS.2021.3100708.
Suhail S., Zeadally S., Jurdak R. et al. Security attacks and solutions for digital twins. Computers in Industry. 2022. Vol. 151. Art. 103961. DOI: 10.1016/j.compind.2023.103961.
Wasim M., Ashraf A., Singh A. et al. A hybrid approach using support vector machine rule-based system: Detecting cyber threats in internet of things. Scientific Reports. 2024. Vol. 14. Art. 78976. DOI: 10.1038/s41598-024-78976-1.
Xu Q., Ali S., Yue T. Digital twin-based anomaly detection with curriculum learning in cyber-physical systems. ACM Transactions on Software Engineering and Methodology. 2023. Vol. 32. Pp. 1–32. DOI: 10.1145/3582571.

digital twin, adaptive threat analysis, smart grid, automated control system, anomaly detection, cyberattack modeling, comparative analysis of strategies, software prototype, synthetic data.