Abstract
Application of convolutional graph neural networks for detecting anomalies in cyber-physical systems is proposed. The graph model reflecting the dynamics of variation in the state of devices is developed, and the algorithm for preprocessing the data providing the generation of the graph on the basis of the studied sample of telemetric indicator values is presented. Using experiments, the optimal parameters of the neural network are determined, the applicability and efficiency of the proposed model for revealing the anomalies in cyber-physical systems are shown, and the capability of the model to reveal and distinguish the classes of attacks is confirmed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Aleksandrova, E.B., Zegzhda, D.P., and Konoplev, A.S., Applying the group signature for entity authentication in distributed grid computing networks, Autom. Control Comput. Sci., 2016, vol. 50, no. 8, pp. 739–742. https://doi.org/10.3103/S0146411616080265
Aleksandrova, E.B., Vasilev, P.N., and Rezedinova, E.U., Extended dynamic revocable BBS group signature scheme, Nonlinear Phenom. Complex Syst. (Minsk, Belarus), 2014, vol. 17, no. 2, pp. 194–202.
Pavlenko, E., Zegzhda, D., and Shtyrkina, A., Criterion of cyber-physical systems sustainability, CEUR Workshop Proc., Moscow, 2019, Basarab, M. and Markov, A.S., Eds., Moscow: CEUR Workshop Proceedings, 2019, pp. 60–64.
Zhou, J., Xu, Z., Rush, A.M., and Yu, M., Automating botnet detection with graph neural networks, 2020. arXiv:2003.06344 [cs.CR]
Lu, L., Safavi-Naini, R., Hagenbuchner, M., Susilo, W., Horton, J., Yong, S.L., and Tsoi, A.C., Ranking attack graphs with graph neural networks, Information Security Practice and Experience. ISPEC 2009, Bao, F., Li, H., and Wang, G., Eds., Lecture Notes in Computer Science, vol. 5451, Berlin: Springer, 2009, pp. 345–359. https://doi.org/10.1007/978-3-642-00843-6_30
Drosou, A., et al., Cross-layer anomaly detection framework, Horizon 2020, Research and Innovation Programme. 20019. https://ec.europa.eu/research/participants/documents/downloadPublic?documentIds= 080166e5c5665c90&appId=PPGMS.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., and Yu, P.S., A comprehensive survey on graph neural networks, IEEE Trans. Neural Networks Learn. Syst., 2020, vol. 32, no. 1, pp. 4–24. https://doi.org/10.1109/TNNLS.2020.2978386
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., and Dahl, G.E., Neural message passing for quantum chemistry, Proc. Mach. Learn. Res., 2017, vol. 70, pp. 1263–1272. https://proceedings.mlr.press/v70/gilmer17a.html
Wu, L., Sun, P., Hong, R., Fu, Y., Wang, X., and Wang, M., SocialGCN: An efficient graph convolutional network-based model for social recommendation, 2018. arXiv:1811.02815 [cs.IR]
Defferrard, M., Bresson, X., and Vandergheynst, P., Convolutional neural networks on graphs with fast localized spectral filtering, Advances in Neural Information Processing Systems, Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., and Garnett, R., Curran Associates, 2016, vol. 29. https://proceedings.neurips.cc/paper/2016/file/ 04df4d434d481c5bb723be1b6df1ee65-Paper.pdf
Nour, M., New generations of Internet of Things datasets for cybersecurity applications based machine learning: TON_IoT Datasets, eResearch Australasia Conf., Brisbane, Australia, 2019, pp. 21–25.
Funding
The study was carried out as part of a scholarship of the President of the Russian Federation to young scientists and graduate students SP-1932.2019.5.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by E. Oborin
About this article
Cite this article
Vasil’eva, K.V., Lavrova, D.S. Detecting Anomalies in Cyber-Physical Systems Using Graph Neural Networks. Aut. Control Comp. Sci. 55, 1051–1060 (2021). https://doi.org/10.3103/S0146411621080320
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411621080320