Abstract
The application of multiagent reinforcement learning technology to solve the problem of intrusion detection in the Internet of Things (IoT) systems is considered. Three models of a multiagent intrusion detection system are implemented: a completely decentralized system, a system with the transfer of forecast data, and a system with the transfer of observation data. The experimental results are given in comparison with the Suricata open-code intrusion detection system. The considered architectures of multiagent systems are shown to be free from the shortcomings of the existing solutions.
REFERENCES
Sinha, S., State of IoT 2021: Number of connected IoT devices growing 9% to 12.3 billion globally, cellular IoT now surpassing 2 billion. https://iot-analytics.com/number-connected-iot-devices/.
2020 SonicWall Cyber Threat Report. https://www.sonicwall.com/resources/white-papers/2020-sonicwall-cyber-threat-report/gated/.
Aleksandrov, D.V. and Sawicki, M., Statement of the problem of modelling of multicomponent cloud-based intelligent IoT systems, 2016, pp. 177–180.
Li, T., Zhu, K., Luong, N.C., Niyato, D., Wu, Q., Zhang, Ya., and Chen, B., Applications of multi-agent reinforcement learning in future internet: A comprehensive survey, IEEE Commun. Surv. Tutorials, 2022, vol. 24, no. 2, pp. 1240–1279. https://doi.org/10.1109/COMST.2022.3160697
Dakhnovich, A.D., Moskvin, D.A., and Zegzhda, D.P., Analysis of the information security threats in the digital production networks, Autom. Control Comput. Sci., 2018, vol. 52, no. 8, pp. 1071–1075. https://doi.org/10.3103/s0146411618080369
Dakhnovich, A.D., Moskvin, D.A., and Zegzhda, D.P., Using security-through-obscurity principle in an industrial internet of things, Autom. Control Comput. Sci., 2021, vol. 55, no. 8, pp. 1061–1067. https://doi.org/10.3103/s0146411621080083
Dakhnovich, A., Moskvin, D., and Zegzhda, D., A necessary condition for industrial internet of things sustainability, Mobile Internet Security. MobiSec 2021, You, I., Kim, H., Youn, T.Y., Palmieri, F., and Kotenko, I., Eds., Communications in Computer and Information Science, vol. 1544, Singapore: Springer, 2022, pp. 79–89. https://doi.org/10.1007/978-981-16-9576-6_7
Dakhnovich, A.D., Moskvin, D.A., and Zegzhda, D.P., Requirements on providing a sustainability of industrial internet of things, Autom. Control Comput. Sci., 2021, vol. 55, no. 8, pp. 956–961. https://doi.org/10.3103/s0146411621080071
Mlytics. DDoS Protection. https://www.mlytics.com/features/ddos-protection.
Anirudh, M., Thileeban, S.A., and Nallathambi, D.J., Use of honeypots for mitigating DoS attacks targeted on IoT networks, 2017 Int. Conf. on Computer, Communication and Signal Processing (ICCCSP), Chennai, India, 2017, India: IEEE, 2017, p. 10. https://doi.org/10.1109/icccsp.2017.7944057
Hossen, H., Analysis of network intrusion detection system with machine learning algorithms (deep reinforcement learning algorithm), Cand. Sci. (Eng.) Dissertation, Moscow: 2018, pp. 23–54.
Xia, S., Bai, W., Zhou, X., Pan, Z., and Guo, S., Defending network traffic attack with distributed multi-agent reinforcement learning, 2019, vol. 1001, pp. 212–225.
Alavizadeh, Hooman., Alavizadeh, Hootan., and Jang-Jaccard, J., Deep Q-learning based reinforcement learning approach for network intrusion detection, Computers, 2022, vol. 11, no. 3, p. 41. https://doi.org/10.3390/computers11030041
Van Hasselt, H., Guez, A., and Silver, D., Deep reinforcement learning with double Q-learning, Proc. AAAI Conf. Artif. Intell., 2016, vol. 30, no. 1, pp. 2094–2100. https://doi.org/10.1609/aaai.v30i1.10295
Gawłowicz, P. and Zubow, A., ns-3 meets OpenAI Gym: The playground for machine learning in networking research, Proc. 22nd Int. ACM Conf. on Modeling, Analysis and Simulation of Wireless and Mobile Systems, Miami Beach, Fla., 2019, New York: Association for Computing Machinery, 2019, pp. 113–120. https://doi.org/10.1145/3345768.3355908
NetAnim 3.108. https://www.nsnam.org.
Funding
The research is funded by the Ministry of Science and Higher Education of the Russian Federation as part of the World-class Research Center program: Advanced Digital Technologies (contract no. 075-15-2022-311 dated 20.04.2022).
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
Kalinin, M.O., Tkacheva, E.I. A Decentralized Approach to Intrusion Detection in Dynamic Networks of the Internet of Things Based on Multiagent Reinforcement Learning with Interagent Interaction. Aut. Control Comp. Sci. 57, 1025–1032 (2023). https://doi.org/10.3103/S0146411623080096
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411623080096