Abstract
This paper presents a model of threats in cyber-physical systems (CPSs) with examples of attacks and potential negative consequences for systems for various purposes. It is concluded that the critical consequences of attacks are associated with data exchange breaches within a system. Therefore, the CPS security problem is confined to restoring the data exchange efficiency. To neutralize the consequences, which are negative for data exchange, it is proposed to use graph artificial neural networks (ANNs). The contemporary architectures of graph ANNs are reviewed. An algorithm for the generation of a synthetic training dataset is developed and implemented to model the network traffic intensity and load of devices in a system based on graph centrality measures. A graph ANN is trained for the problem of reconfiguring the graph of a CPS.
REFERENCES
Lavrova, D.S. and Shtyrkina, A.A., The analysis of artificial neural network structure recovery possibilities based on the theory of graphs, Autom. Control Comput. Sci., 2020, vol. 54, no. 8, pp. 977–982. https://doi.org/10.3103/s0146411620080222
Aleksandrova, E.B. and Shtyrkina, A.A., Graph model for cyber-physical systems security, Cyber-Physical Systems and Control II, Arseniev, D.G. and Aouf, N., Eds., Lecture Notes in Networks and Systems, vol. 460, Cham: Springer, 2023, pp. 458–464. https://doi.org/10.1007/978-3-031-20875-1_42
Dong, G., Tang, M., Wang, Z., Gao, J., Guo, S., Cai, L., Gutierrez, R., Campbel, B., Barnes, L.E., and Boukhechba, M., Graph neural networks in IoT: A survey, ACM Trans. Sen. Netw., 2023, vol. 19, no. 2, p. 47. https://doi.org/10.1145/3565973
‘Dangerous stuff’: Hacker tried to poison water supply of Florida town, New Y. Times. https://www.nytimes. com/2021/02/08/us/oldsmar-florida-water-supply-hack.html. Cited August, 2022.
Nazarenko, A.A. and Safdar, G.A., Survey on security and privacy issues in cyber physical systems, AIMS Electron. Electr. Eng., 2019, vol. 3, no. 2, pp. 111–143. https://doi.org/10.3934/electreng.2019.2.111
Pavlenko, E.Y., Vasileva, K.V., Lavrova, D.S., and Zegzhda, D.P., Counteraction the cybersecurity threats of the in-vehicle local network, J. Comput. Virol. Hacking Tech., 2023, vol. 19, no. 3, pp. 399–408. https://doi.org/10.1007/s11416-022-00451-0
Tsilikov, N.S. and Fedosin, S.A., Graph neural networks, Inzh. Tekhnol. Sist., 2012, no. 2, pp. 161–163.
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., and Monfardini, G., The graph neural network model, IEEE Trans. Neural Networks, 2009, vol. 20, no. 1, pp. 61–80. https://doi.org/10.1109/tnn.2008.2005605
Kipf, T.N. and Welling, M., Variational graph auto-encoders, 2016. https://doi.org/10.48550/arXiv.1611.07308
Guo, X., Zhao, L., Nowzari, C., Rafatirad, S., Homayoun, H., and Pudukotai Dinakarrao, S.M., Deep multi-attributed graph translation with node-edge co-evolution, 2019 IEEE Int. Conf. on Data Mining (ICDM), Beijing, 2019, IEEE, 2019, pp. 250–259. https://doi.org/10.1109/icdm.2019.00035
Zaitseva, E.A., Zegzhda, D.P., and Poltavtseva, M.A., Use of graph representation and case analysis to assess the security of computer systems, Autom. Control Comput. Sci., 2019, vol. 53, no. 8, pp. 937–947. https://doi.org/10.3103/s0146411619080327
Kalinin, M., Demidov, R., and Zegzhda, P., Hybrid neural network model for protection of dynamic cyber infrastructure, Nonlinear Phenom. Complex Syst., 2019, vol. 22, no. 4, pp. 375–382. https://doi.org/10.33581/1561-4085-2019-22-4-375-382
Zegzhda, D.P. and Pavlenko, E.Yu., Cyber-sustainability of software-defined networks based on situational management, Autom. Control Comput. Sci., 2018, vol. 52, no. 8, pp. 984–992. https://doi.org/10.3103/s0146411618080291
Fatin, A.D., Pavlenko, E.Yu., and Poltavtseva, M.A., A survey of mathematical methods for security analysis of cyberphysical systems, Autom. Control Comput. Sci., 2020, vol. 54, no. 8, pp. 983–987. https://doi.org/10.3103/s014641162008012x
Fatin, A.D. and Pavlenko, E.Yu., Using the neat-hypercube mechanism to detect cyber attacks on IoT systems, Autom. Control Comput. Sci., 2021, vol. 55, no. 8, pp. 1111–1114. https://doi.org/10.3103/s0146411621080101
Pavlenko, E.Yu., Yarmak, A.V., and Moskvin, D.A., Hierarchical approach to analyzing security breaches in information systems, Autom. Control Comput. Sci., 2017, vol. 51, no. 8, pp. 829–834. https://doi.org/10.3103/s0146411617080144
Funding
This study was supported by the Ministry of Science and Higher Education of the Russian Federation as a part of the World-Class Research Center Program “Advanced Digital Technologies” (contract no. 075-15-2022-311 dated from April 20, 2022).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Translated by E. Glushachenkova
Publisher’s Note.
Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Aleksandrova, E.B., Shtyrkina, A.A. Method for the Adaptive Neutralization of Structural Breaches in Cyber-Physical Systems Based on Graph Artificial Neural Networks. Aut. Control Comp. Sci. 57, 1076–1083 (2023). https://doi.org/10.3103/S0146411623080011
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411623080011