Authors : Shaban Somah Amadu; Bernice Asantewaa Kyere

Volume/Issue : Volume 10 - 2025, Issue 10 - October

Google Scholar : https://tinyurl.com/rff29rk4

Scribd : https://tinyurl.com/yc37aru5

DOI : https://doi.org/10.38124/ijisrt/25oct1263

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : This paper presents a secure digital twin framework that integrates Petri Net process modeling with artificial intelligence–driven anomaly detection to protect cyber-aware business workflows. The approach begins by preprocessing the dataset and extracting more than eighty flow-level features such as timing, packet sizes, and TCP flags. The framework integrates Petri Nets with dual AI detectors using CIC-IDS2021 traffic data. Two complementary detectors, a Long Short- Term Memory Autoencoder and an Isolation Forest, learn normal traffic patterns and generate real-time anomaly scores. These scores dynamically influence the digital twin by controlling Petri Net transition guards and adaptive firing rates, while the overall system behavior is modeled as a continuous-time Markov chain to evaluate long-term risk and cost trade-offs. The proposed AI-integrated digital twin achieved an F1-score of 0.96 and an ROC-AUC of 0.98, outperforming static Petri Nets with an F1-score of 0.76 and ROC-AUC of 0.79 and stand-alone AI with an F1-score of 0.92 and ROC-AUC of 0.96. It reduced mean time to detection to 3.1 seconds and extended mean time to compromise to 11.7 seconds, while Markov chain risk analysis showed the compromise probability falling from 0.43 to below 0.02 with moderate security investment. These results demonstrate that combining explainable Petri Nets with adaptive artificial intelligence analytics creates an economically optimized, interpretable, and resilient cybersecurity strategy for complex business processes and modern Industry 4.0 systems.

Keywords : Secure Digital Twin, Petri Nets, AI-Driven Anomaly Detection, Continuous-Time Markov Chain and Cyber-Aware Business Processes.

References :

1. Ahmed, M., Mahmood, A. N., & Hu, J. (2021). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 173, 102871. https://doi.org/10.1016/j.jnca.2020.102871
2. Alcaraz, C., & Zeadally, S. (2020). Critical infrastructure protection: Requirements and challenges for the 21st century. Computers & Security, 98, 102081. https://doi.org/10.1016/j.cose.2020.102081
3. Alsaedi, N., Moustafa, N., & Tari, Z. (2022). Anomaly detection for industrial IoT systems using autoencoder neural networks. IEEE Internet of Things Journal, 9(14), 12236–12249. https://doi.org/10.1109/JIOT.2022.3145902
4. Ammar, A., Derigent, W., & Levrat, E. (2021). A review of digital twin: Definitions, characteristics, applications, and design implications. IEEE Access, 9, 117756–117772. https://doi.org/10.1109/ACCESS.2021.3102130
5. Banaeian Far, M., & Rinner, B. (2023). Explainable artificial intelligence for intrusion detection: A survey and outlook. ACM Computing Surveys, 55(12), 1–38. https://doi.org/10.1145/3533811
6. Basile, F., Chiacchio, P., & Gerbasio, D. (2019). Modeling and analysis of cyber-physical production systems using Petri nets. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(1), 120–132. https://doi.org/10.1109/TSMC.2017.2751681
7. Bozic, J., Pieters, W., & Wieringa, R. (2020). Petri nets for security risk assessment and mitigation. Information and Software Technology, 122, 106280. https://doi.org/10.1016/j.infsof.2020.106280
8. Cao, K., Liu, Y., Meng, G., & Sun, Q. (2022). Real-time digital twin for cyber-physical production systems. IEEE Transactions on Industrial Informatics, 18(5), 3116–3126. https://doi.org/10.1109/TII.2021.3053613
9. Canadian Institute for Cybersecurity. (2021). CIC-IDS2021 dataset. Retrieved from https://www.unb.ca/cic/datasets/ids-2021.html
10. Chicone, C., & He, D. (2021). Stochastic modeling and control in cyber-physical systems. IEEE Transactions on Automatic Control, 66(9), 4303–4316. https://doi.org/10.1109/TAC.2020.3046415
11. Deng, H., Zhang, Y., & Chen, X. (2020). Hybrid deep learning for network intrusion detection using CIC-IDS2021. IEEE Access, 8, 170509–170519. https://doi.org/10.1109/ACCESS.2020.3025005
12. Ding, K., Chan, F. T. S., & Zhang, X. (2022). A review of digital twin modeling methods for cyber-physical systems. Advanced Engineering Informatics, 52, 101624. https://doi.org/10.1016/j.aei.2022.101624
13. Ghosh, S., & Grolinger, K. (2021). Deep learning for intrusion detection in industrial control systems: A review. IEEE Transactions on Industrial Informatics, 17(9), 6134–6149. https://doi.org/10.1109/TII.2021.3054071
14. Giraldo, J., Sarkar, E., & Cárdenas, A. A. (2020). Security and resilience of cyber-physical systems: A review. ACM Computing Surveys, 53(3), 1–36. https://doi.org/10.1145/3391197
15. He, H., & Chen, S. (2021). Isolation forest-based anomaly detection for cyber-physical systems. Future Generation Computer Systems, 118, 478–489. https://doi.org/10.1016/j.future.2021.01.024
16. Horkoff, J., & Giorgini, P. (2022). Goal-oriented modeling for cybersecurity risk analysis. Computers & Security, 113, 102540. https://doi.org/10.1016/j.cose.2021.102540
17. Jiang, Y., Wu, Y., & Wang, J. (2023). Online adaptive intrusion detection using deep autoencoders and streaming analytics. IEEE Internet of Things Journal, 10(6), 5179–5188. https://doi.org/10.1109/JIOT.2022.3174328
18. Lee, J., Bagheri, B., & Kao, H. A. (2020). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 20, 34–39. https://doi.org/10.1016/j.mfglet.2020.02.002
19. Li, X., Han, Y., & Zhao, Z. (2022). Explainable deep learning for anomaly detection in IoT. IEEE Access, 10, 25632–25645. https://doi.org/10.1109/ACCESS.2022.3147773
20. Mavridis, N., & Spanoudakis, G. (2022). Petri nets and Markov modeling for risk-aware business workflows. Information Systems, 104, 101908. https://doi.org/10.1016/j.is.2021.101908
21. Meidan, Y., Bohadana, M., & Hadar, E. (2020). Detection of IoT botnet attacks using deep autoencoders. Computers & Security, 96, 101935. https://doi.org/10.1016/j.cose.2020.101935
22. Moustafa, N., Turnbull, B., & Camtepe, S. (2021). Evaluation of anomaly detection algorithms with new generation datasets: CIC-IDS2021 and TON_IoT. IEEE Access, 9, 56740–56760. https://doi.org/10.1109/ACCESS.2021.3073433
23. Papadopoulos, G., & Tselikas, N. D. (2019). Digital twins in security and predictive maintenance. Sensors, 19(14), 3118. https://doi.org/10.3390/s19143118
24. Qi, Q., & Tao, F. (2021). Digital twin and big data towards smart manufacturing and industry 4.0. IEEE Access, 9, 141957–141972. https://doi.org/10.1109/ACCESS.2021.3118841
25. Sarker, I. H., & Abawajy, J. (2021). A review on AI-driven intrusion detection and prevention in cyber-physical systems. ACM Computing Surveys, 54(6), 1–37. https://doi.org/10.1145/3453153
26. Shi, W., Cao, J., & Zhang, Q. (2022). Digital twin for industrial cybersecurity: A survey and future directions. IEEE Transactions on Industrial Informatics, 18(10), 6753–6764. https://doi.org/10.1109/TII.2022.3153891
27. Sun, Y., Liu, S., & Jiang, C. (2021). Deep learning-based intrusion detection in the presence of concept drift. IEEE Transactions on Network and Service Management, 18(2), 1956–1968. https://doi.org/10.1109/TNSM.2021.3066071
28. Tang, T. A., Mhamdi, L., & McLernon, D. (2019). Deep learning approaches for anomaly-based intrusion detection systems: A survey. IEEE Access, 7, 78247–78266. https://doi.org/10.1109/ACCESS.2019.2928662
29. Tao, F., Zhang, H., & Qi, Q. (2022). Five-dimensional digital twin model and its applications in cyber-physical systems. Advanced Engineering Informatics, 52, 101625. https://doi.org/10.1016/j.aei.2022.101625
30. Ullah, A., Ahmad, J., & Kim, D. (2023). Explainable deep learning for ICS intrusion detection: A hybrid approach. Computers & Security, 125, 103038. https://doi.org/10.1016/j.cose.2022.103038
31. Wang, Y., & Xu, Z. (2020). Modeling and optimizing cyber-physical workflows using stochastic Petri nets. Future Generation Computer Systems, 113, 369–382. https://doi.org/10.1016/j.future.2020.06.028
32. Xu, L. D., He, W., & Li, S. (2021). Internet of Things and big data analytics for smart and connected communities. IEEE Internet of Things Journal, 8(12), 9739–9752. https://doi.org/10.1109/JIOT.2020.3032671
33. Yang, H., & Kim, H. (2022). Anomaly detection in IoT networks using hybrid autoencoder and isolation forest. Sensors, 22(6), 2261. https://doi.org/10.3390/s22062261
34. Zawodniok, M., & Melliar-Smith, P. M. (2021). Applying stochastic Petri nets to cyber-physical systems security analysis. IEEE Transactions on Reliability, 70(3), 1113–1128. https://doi.org/10.1109/TR.2020.3033941
35. Zhang, H., Sun, Y., & Liu, Q. (2023). Digital twin-driven cyber defense using explainable machine learning. IEEE Access, 11, 121304–121319. https://doi.org/10.1109/ACCESS.2023.3278561