Neuro-symbolic models for ensuring cybersecurity in critical cyber-physical systems

2024;
: pp. 42-50
1
Department of Computer Science and Software Engineering, Kherson State University

This paper presents the results of a comprehensive study on the application of the neuro-symbolic approach for detecting and preventing cyber threats in railway systems, a critical component of cyber-physical infrastructures. The increasing complexity and integration of physical systems with digital technologies have made such infrastructures vulnerable to cyberattacks, where breaches can result in severe consequences, including system failures, financial losses, and threats to public safety and the environment. The objective of this study was to assess the effectiveness of the neuro-symbolic approach, which combines artificial neural networks with symbolic algorithms, in detecting and mitigating cyber threats in dynamic environments. The methodology involved simulating various cyberattack scenarios on a test architecture for railway system security, followed by applying the neuro-symbolic model for threat detection and response. Results showed that the neuro-symbolic approach demonstrated high accuracy in detecting cyber threats and was particularly effective in adapting to new and unknown types of attacks. Compared to traditional methods, this approach significantly improved detection efficiency and response speed. The findings confirm that the neuro-symbolic approach enhances cybersecurity, particularly in critical infrastructures like railway systems, and contributes to more reliable protection of data related to passengers and transported goods. Further research will focus on optimizing the implementation of these algorithms and expanding the range of practical applications to other critical sectors.

  1. Alex. Taylor, "Neuro-Symbolic Methods for Cyber Secu-rity", Journal of Artificial Intelligence Research, vol. 12, no. 3, pp. 500-515, 2021.
  2. H. Alashkar and M. Ahmad, “A Comprehensive Review on Machine Learning Techniques for Cyber-Physical Sys-tems”, Journal of Systems Architecture, vol. 129, pp. 102649, 2023. 
  3. A. Mishra and R. Gupta, “An Overview of Cyber-Physical Systems: Applications, Challenges, and Future Direc-tions”, ACM Computing Surveys, , vol. 55, no. 9, pp. 1–35, 2022.  https://doi.org/10.1145/3498707
  4. C. Vural and U. Akbulut, “Cyber-Physical Systems Security: Threats and Machine Learning Countermeasures”, IEEE Transactions on Emerging Topics in Computing, , vol. 11, no. 2, pp. 417–426, 2023. 
  5. S. Garfinkel, C. Adams, and J. Warfield, “Under-standing cyber-physical attacks and defenses”. IEEE Secu-rity & Privacy, vol.12, no.1, pp. 20-26, 2014.
  6. Wei Zhang, et al. "Adaptive Security Models for Cyber-Physical Systems", in Trends in Cyber-Physical Systems Security, edited by Laura Brown, Cham: Springer, vol. 5, pp. 200-215, 2022.
  7. Sarah White, et al., "Challenges in Protecting Railway Infrastructure", Transport Security Journal, vol. 6, no. 4, pp. 210-225, 2020.
  8. S. O. Yevdokymov, Modern systems of information pro-tection. - Kyiv: Drukaryk, p. 380, 2023.
  9. S. O. Yevdokymov, Applied systems for choosing the optimal route in transport. - Kyiv: FOP Gu-lyaeva V.M., p. 200, 2024.
  10. Sam. Parker, The Role of Cryptography in Securing Cyber-Physical Systems, In Cyber Security: Principles and Practices, edited by Alan Richards, New York: Wiley, pp. 130-150, 2021.
  11. M. A. Khan and S.Ali, “Machine Learning for Cybersecurity in Cyber-Physical Systems: Recent Advances and Future Directions”, Journal of Network and Computer Applica-tions, vol. 209, pp. 103531, 2023. 
  12. A. Sahu and S. Dutta, “Emerging Trends in Cyber-Physical Systems Security: A Review of Machine Learning Solu-tions”, Computers & Security, vol. 114, pp. 103701, 2022. 
  13.  R. Kumar and A.Tripathi, “Anomaly Detection in Cyber-Physical Systems Using Ensemble Learning Techniques”, IEEE Transactions on Industrial Informatics, , vol. 19, no. 2, pp. 1253–1263, 2023. 
  14. Laura Green, et al. "Real-Time Threat Detection in Cyber-Physical Systems", Journal of Cyber Security, vol. 15, no. 2, pp. 200-210, 2021.
  15. H. Zhang and J.Xu, “Neural-Symbolic Approaches for Cyber-Physical Systems: Enhancing Anomaly Detection”, Artifi-cial Intelligence Review, vol. 56, no. 1, pp. 321–347, 2023. 
  16. G. Katz, et al. "Combining Neural Networks and Sym-bolic Reasoning for Enhanced Security in Cyber-Physical Systems", in Proc. International Conference on Neural Information Processing Systems (NeurIPS), pp. 234-246, 2023.
  17. S. O. Yevdokymov, System programming: Creating appli-cations on Assembler,  2nd ed., supplemented and revised. - London, United Kingdom: LAP LAMBERT Academic Publishing, p. 133, 2024.
  18. Mark Johnson, "Ensuring Data Integrity and Confidenti-ality in Cyber-Physical Systems." International Journal of Cyber Security, vol. 8, no. 3, pp. 300-315, 2022.
  19. M. M. Rahman and A. Saha, “Anomaly Detection in Cyber-Physical Systems: A Hybrid Approach”, Future Genera-tion Computer Systems, , vol. 128, pp. 132–146, 2022. 
  20. Jane Smith, "Securing Industrial Control Systems: A Case Study", in Proc. International Conference on Cyber Security, pp. 123-130, 2020.
  21. S. McLaughlin, K. Lucas, J. Sorber, J. Jiang, , and S. Krish-nan, “Cyber-physical systems and big data: A voluminous challenge”, ACM Transactions on Cyber-Physical Systems, vol. 1, no. 1, p. 4, 2017.
  22. A. Sharma and A.Kumar, “Deep Learning Techniques for Real-Time Anomaly Detection in Cyber-Physical Sys-tems”, IEEE Access, vol. 11, pp. 114202–114218, 2023. 
  23. V. A. Smyrnov and M. O. Doroshenko, “Use of neurosymbolic technologies in transport cyber security systems”, Scientific Bulletin of the Uzhhorod National University, vol.1, no. 1, pp. 89–95, 2023.