Data-Based Detection of Antagonistic Agents in a Robot Swarm Solving a Dynamic Coverage Task

Abstract

Robot swarms can be deployed as moving surveillance systems, for instance, as mobile anti-poaching systems for monitoring wildlife and detecting poaching activities. Since poachers have an interest in evading detection, robots are at risk of being hijacked and manipulated to behave antagonistically, for example, to prevent the correct surveillance of a group of animals in a certain area. While the detection of cyber-attacks on robots is commonly considered in the context of network activity and communication, this work focuses on the detection of anomalies that manifest in the robots' physical motion behavior. It builds upon our previous work, where a contextual data-driven anomaly detection method was proposed and applied to motions of a robot swarm monitoring a static area. Such data-driven, unsupervised methods for detecting anomalies in the physical behavior of robots are a suitable way of evading the need to define behavioral signatures or rules but only use information on the behavior of “normal,” cooperating robots, and the method proposed earlier demonstrated a strong performance both for recognizing normal robots and for the detection of a single antagonistic robot within a swarm monitoring a static area. Motivated by anti-poaching scenarios, this article goes beyond the earlier work by considering multiple antagonists and a dynamic scenario, where the robots monitor a continually changing area around a herd of animals and therefore do not converge to fixed, optimal positions as in a static scenario. The statistical evaluation shows that the anomaly detection method consistently yields a correct categorization of normal and antagonistic behavior, and that the method's performance is unaffected by an increased number of antagonistic robots in a swarm. Furthermore, the results indicate that, given the availability of a limited amount of new data, the method can be fine-tuned to efficiently adapt to new settings.

Keywords

anomaly detection / antagonistic behavior / anti-poaching system / density estimation / robot swarm / wildlife conservation

References

[1] J. C. Van Gemert, C. R. Verschoor, P. Mettes, K. Epema, L. P. Koh, and S. Wich, “Nature Conservation Drones for Automatic Localization and Counting of Animals,” in Computer Vision - ECCV 2014 Workshops, eds. L. Agapito, M. M. Bronstein, and C. Rother, 8925 (Springer Int. Publishing, 2015), 255–270. https://doi.org/10.1007/978-3-319-16178-5_17.

[2] M. A. Olivares-Mendez, C. Fu, P. Ludivig, et al., “Towards an Autonomous Vision-Based Unmanned Aerial System Against Wildlife Poachers,” Sensors 15, no. 12 (2015): 31362–31391, https://doi.org/10.3390/s151229861.

[3] J. Kamminga, E. Ayele, N. Meratnia, and P. Havinga, “Poaching Detection Technologies—A Survey,” Sensors 18, no. 5 (2018): 1474, https://doi.org/10.3390/s18051474.

[4] A. J. Plumptre, B. Dilkina, F. Fang, and M. Tambe, “Automatic Detection of Poachers and Wildlife With UAVs,” in Artificial Intelligence and Conservation, eds. A. J. Plumptre, B. Dilkina, F. Fang, and M. Tambe (Cambridge University Press, 2019), 77–100. https://doi.org/10.1017/9781108587792.006.

[5] Wildlife Conservation UAV Challenge. Available Online, accessed December 23, 2025, https://www.kashmirworldfoundation.org/Projects/wildlife-conservation-uav-challenge.

[6] Air Shepherd Project, accessed December 23, 2025, https://www.airshepherd.org/.

[7] S. Anbalagan, W. Alhakami, A. Manoharan, et al., “TVUB: Thermal Vision-Based UAV and Blockchain-Aided Poaching Prevention System,” in GLOBECOM 2023-2023 (IEEE Global Communications Conference, 2023), 1296–1301. https://doi.org/10.1109/GLOBECOM54140.2023.10437160.

[8] U. Zengin and A. Dogan, “Cooperative Target Pursuit by Multiple UAVs in an Adversarial Environment,” Robotics and Autonomous Systems 59, no. 12 (2011): 1049–1059, https://doi.org/10.1016/j.robot.2011.08.006.

[9] C. Rani, H. Modares, R. Sriram, D. Mikulski, and F. L. Lewis, “Security of Unmanned Aerial Vehicle Systems Against Cyber-Physical Attacks,” Journal of Defense Modeling and Simulation: Applications, Methodology, Technology 13, no. 3 (2016): 331–342, https://doi.org/10.1177/1548512915617252.

[10] K. Hartmann and K. Giles, “UAV Exploitation: A New Domain for Cyber Power,” in 8th International Conference on Cyber Conflict (CyCon) (2016), 205–221. https://doi.org/10.1109/CYCON.2016.7529436.

[11] R. Altawy and A. M. Youssef, “Security, Privacy, and Safety Aspects of Civilian Drones: A Survey,” ACM Transactions on Cyber-Physical Systems 1, no. 2 (2017): 1–25, https://doi.org/10.1145/3001836.

[12] O. Westerlund and R. Asif, “Drone Hacking With Raspberry-Pi 3 and WiFi Pineapple: Security and Privacy Threats for the Internet-of-Things,” in 1st International Conference on Unmanned Vehicle Systems-Oman (UVS) (2019), 1–10. https://doi.org/10.1109/UVS.2019.8658279.

[13] J. P. Yaacoub, H. Noura, O. Salman, and A. Chehab, “Security Analysis of Drones Systems: Attacks, Limitations, and Recommendations,” Internet of Things 11 (2020): e100218, https://doi.org/10.1016/j.iot.2020.100218.

[14] E. Basan, A. Basan, and A. Nekrasov, “Method for Detecting Abnormal Activity in a Group of Mobile Robots,” Sensors 19, no. 18 (2019): e4007, https://doi.org/10.3390/s19184007.

[15] G. Deng, Y. Zhou, Y. Xu, T. Zhang, and Y. Liu, “An Investigation of Byzantine Threats in Multi-Robot Systems,” in 24th International Symposium on Research in Attacks, Intrusions and Defenses (ACM, 2021), 17–32. https://doi.org/10.1145/3471621.3471867.

[16] K. Saulnier, D. Saldaña, A. Prorok, G. J. Pappas, and V. Kumar, “Resilient Flocking for Mobile Robot Teams,” IEEE Robotics and Automation Letters 2, no. 2 (2017): 1039–1046, https://doi.org/10.1109/LRA.2017.2655142.

[17] P. Zhang, C. Hu, S. Wu, R. Gong, and Z. Luo, “Event-Triggered Resilient Average Consensus With Adversary Detection in the Presence of Byzantine Agents,” IEEE Access 9 (2021): 121431–121444, https://doi.org/10.1109/ACCESS.2021.3108639.

[18] M. Cavorsi, O. E. Akgün, M. Yemini, A. J. Goldsmith, and S. Gil, “Exploiting Trust for Resilient Hypothesis Testing With Malicious Robots,” in 2023 IEEE International Conference on Robotics and Automation (ICRA) (2023), 7663–7669. https://doi.org/10.1109/ICRA48891.2023.10160385.

[19] H. R. Babaei Ghazvini and M. Haeri, “Byzantine Agents' Detection in Distributed Nash Equilibrium Seeking Algorithms Using an Adaptive Event-Triggered Scheme,” IEEE Systems Journal 17, no. 3 (2023): 4407–4418, https://doi.org/10.1109/JSYST.2023.3267160.

[20] A. Fagiolini, F. Babboni, and A. Bicchi, “Dynamic Distributed Intrusion Detection for Secure Multi-Robot Systems,” in 2009 IEEE International Conference on Robotics and Automation (IEEE, 2009), 2723–2728. https://doi.org/10.1109/ROBOT.2009.5152608.

[21] H. Sedjelmaci, S. M. Senouci, and N. Ansari, “A Hierarchical Detection and Response System to Enhance Security Against Lethal Cyber-Attacks in UAV Networks,” IEEE Transactions on Systems, Man, and Cybernetics: Systems 48, no. 9 (2018): 1594–1606, https://doi.org/10.1109/TSMC.2017.2681698.

[22] I. Sargeant and A. Tomlinson, “Intrusion Detection in Robotic Swarms,” in Intelligent Systems and Applications, eds. Y. Bi, R. Bhatia, and S. Kapoor, 1038 (Springer International Publishing, 2020), 968–980. https://doi.org/10.1007/978-3-030-29513-4_71.

[23] I. Wenger, P. Eberhard, and H. Ebel, “Discovering Antagonists in Networks of Systems: Robot Deployment,” Robotics and Autonomous Systems 196 (2026): e105235, https://doi.org/10.1016/j.robot.2025.105235.

[24] I. Aoki, “A Simulation Study on the Schooling Mechanism in Fish,” Nippon Suisan Gakkaishi 48, no. 8 (1982): 1081–1088, https://doi.org/10.2331/suisan.48.1081.

[25] I. Wenger, H. Ebel, and P. Eberhard, “Anomalously Acting Agents: The Deployment Problem,” Multibody System Dynamics 64 (2025): 465–483, https://doi.org/10.1007/s11044-024-09993-1.

[26] S. Lloyd, “Least Squares Quantization in PCM,” IEEE Transactions on Information Theory 28, no. 2 (1982): 129–137, https://doi.org/10.1109/TIT.1982.1056489.

[27] G. Voronoi, “Nouvelles applications des paramètres continus à la théorie des formes quadratiques. Premier Mémoire. Sur quelques propriétés des formes quadratiques positives parfaites,” Journal für die reine und angewandte Mathematik (Crelles Journal) 1908, no. 133 (1908): 97–102, https://doi.org/10.1515/crll.1908.133.97.

[28] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation 9, no. 8 (1997): 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735.

[29] E. G. Tabak and C. V. Turner, “A Family of Nonparametric Density Estimation Algorithms,” Communications on Pure and Applied Mathematics 66, no. 2 (2013): 145–164, https://doi.org/10.1002/cpa.21423.

[30] D. J. Rezende and S. Mohamed, “Variational Inference With Normalizing Flows,” in Proceedings of the 32nd International Conference on Machine Learning, eds. F. Bach and D. Blei, 37 (2015), 1530–1538. https://doi.org/10.48550/arXiv.1505.05770.

[31] L. Biewald, “Experiment Tracking With Weights and Biases.” https://pypi.org/project/wandb/ (2020), 0.16.1.

[32] K. Pearson, “VII. Note on Regression and Inheritance in the Case of Two Parents,” Proceedings of the Royal Society of London 58, no. 347–352 (1895): 240–242, https://doi.org/10.1098/rspl.1895.0041.

RIGHTS & PERMISSIONS

2026 The Author(s). International Journal of Mechanical System Dynamics published by John Wiley & Sons Australia, Ltd on behalf of Nanjing University of Science and Technology.