Method for detecting malicious robots in the collective perception of the environment

Zikratov I.A., Zikratova T.V. Method for detecting malicious robots in the collective perception of the environment. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2026, vol. 26, no. 3, pp. 532–543 (in Russian). doi: 10.17586/2226-1494-2026-26-3-532-543

Multi-variant collective decision-making in multi-agent robotic systems is a complex problem of swarm intelligence. The architectural features of homogeneous robot groups with decentralized control and the limited capabilities of individual agents provide an opportunity for attackers to introduce and use malicious robots within the swarm. Malicious robots employ various behavioral strategies and create conditions for erroneous decision-making during consensus formation. A method is proposed to detect malicious robots while the swarm performs the task of mapping the original scene. The proposed approach solves the problem of detecting malicious robots within a swarm, regardless of the behavioral strategy they use. The method is based on the hypothesis that the statistical characteristics of local maps obtained by benign robots correspond to the statistical characteristics of the original scene and do not match the characteristics of local maps from malicious robots. Frequency histograms of attributes of the examined object, generated during the analysis of local maps, are proposed as recognition features. The recognition problem is solved using a naive Bayes classifier. This approach ensures high recognition quality by identifying statistically significant differences in the histograms of local maps from benign and malicious robots. The performance metrics of the developed algorithm are evaluated for various scene types. A series of experiments is conducted in which the probability of correctly identifying malicious robots using different behavioral strategies is assessed for the same initial data. It is shown that when the Bayesian classifier is pre-trained on a scene with identical statistical characteristics, the Type II error is reduced to minimal values. Identifying the Type II error is critically important to prevent malicious agents from being admitted to corrective decision-making discussions. The proposed algorithm features a high degree of abstraction, allowing it to be considered for use in a wide range of collective perception tasks involving deliberate malicious information attacks.

1. Sailor M.J., Link J.R. “Smart dust”: nanostructured devices in a grain of sand. Chemical Communications, 2005, vol. 11, pp. 1375–1385. doi: 10.1039/b417554a

2. Kalyaev I.A., Gaiduk A.R., Kapustyan S.G. Models and Algorithms of Collective Control in Groups of Robots. Moscow, Fizmatlit Publ., 2009, 280 p. (in Russian)

3. Gorodetsky V.I. Behavioral model for cyber-physical system and group control: the basic concepts. Izvestiya SFEDU. Engineering Sciences, 2019, no. 1 (203), pp. 144–162. (in Russian). doi: 10.23683/2311-3103-2019-1-144-162

4. Valentini G., Brambilla D., Hamann H., Dorigo M. Collective perception of environmental features in a robot swarm. Lecture Notes in Computer Science, 2016, vol. 9882, pp. 65–76. doi: 10.1007/978-3-319-44427-7_6

5. Valentini G., Hamann H., Dorigo M. Self-organized collective decision making: The weighted voter model. Proc. of the 13^th International Conference on Autonomous Agents and Multiagent Systems, 2014, pp. 45–52. doi: 10.65109/mdde7348

6. Valentini G., Ferrante E., Hamann H., Dorigo M. Collective decision with 100 Kilobots: Speed versus accuracy in binary discrimination problems. Autonomous Agents and Multi-Agent Systems, 2015, vol. 30, no. 3, pp. 553–580. doi: 10.1007/s10458-015-9323-3

7. Castellano C., Fortunato S., Loreto V. Statistical physics of social dynamics. Reviews of Modern Physics, 2009, vol. 81, no. 2, pp. 591–646. doi: 10.1103/revmodphys.81.591

8. Zikratov I.A., Zikratova T.V., Novikov E.A. Implementation of collective perception strategy in a self-organizing swarm system using bayesian decision rule. Proceedings of Telecommunication Universities. 2025, vol. 11, no. 3, pp. 108–118. (in Russian). doi: 10.31854/1813-324X-2025-11-3-108-118

9. Basan A.S., Basan E.A., Makarevich O.B. Analysis of ways to secure group control for autonomous mobile robots. Proc. of the 10^th International Conference on Security of Information and Networks, 2017, pp. 134–139. doi: 10.1145/3136825.3136879

10. Ryabtsev S.S. A method for detecting byzantine robots based on data from the collective decision-making process in swarm robotic systems. Systems of Control, Communication and Security, 2022, no. 3, pp. 105–137. (in Russian). doi: 10.24412/2410-9916-2022-3-105-137

11. Zikratov I.A., Lebedev I.S., Gurtov A.V., Kuzmich E.V. Securing swarm intellect robots with a police office model. Proc. of the IEEE 8^th International Conference on Application of Information and Communication Technologies (AICT), 2014, pp. 1–5. doi: 10.1109/icaict.2014.7035906

12. Guan X., Yang Y., You J. POM-a mobile agent security model against malicious hosts. Proc. of the 4^th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, 2000, vol. 2, pp. 1165–1166. doi: 10.1109/hpc.2000.843621

13. Page J., Zaslavsky A., Indrawan M. A buddy model of security for mobile agent communities operating in pervasive scenarios. Proc. of the 2^nd Australasian Information Security Workshop, 2004, pp. 17–25.

14. Zikratov I.A., Gurtov A.V., Zikratova T.V., Kozlova E.V. Police office model improvement for security of swarm robotic systems. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2014, no. 5 (93), pp. 99–109. (in Russian)

15. Schillo M., Funk P., Rovatsos M. Using trust for detecting deceitful agents in artificial societies. Applied Artificial Intelligence, 2000, vol. 14, no. 8, pp. 825–848. doi:10.1080/08839510050127579

16. Zikratov I.A., Viksnin I.I., Zikratova T.V., Shlykov A.A., Medvedkov D.I. Security model of mobile multi-agent robotic systems with collective management. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2017, vol. 17, no. 3, pp. 439–449. (in Russian). doi: 10.17586/2226-1494-2017-17-3-439-449

17. Strobel V., Dorigo M. Blockchain technology for robot swarms: A shared knowledge and reputation management system for collective estimation. Proc. of the ANTS 2018 11^th International Conference, 2018, pp. 425.

18. Shan Q., Mostaghim S. Discrete collective estimation in swarm robotics with distributed Bayesian belief sharing. Swarm Intelligence, 2021, vol. 15, no. 4, pp. 378–405. doi:10.1007/s11721-021-00201-w

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License