DOI: 10.17587/prin.17.319-333

Distributed Access Control Method for Trusted Interaction of Robotic Agents in a Decentralized Cyber-Physical Environment

V. I. Petrenko¹, Cand. Sc. (Eng.), Head of Department, vipetrenko@ncfu.ru, M. Kh. Najajra², PhD, Associate Professor, mnajajra@pass.ps, F. B. Tebueva¹, D. Sc. (Phys.&Math.), Professor, ftebueva@ncfu.ru, V. I. Pronin¹, Student, vladinfotech23@gmail.com,
¹ North-Caucasus Federal University, Stavropol, 355017, Russian Federation
² Al-Istiqlal University, Jericho, P583, Palestine

Corresponding author: Fariza B. Tebueva, D. Sc. (Phys.-Math.), Professor, North-Caucasus Federal University, Stavropol, 355017, Russian Federation, E-mail: ftebueva@ncfu.ru

The article presents an innovative method for distributed access control of robotic agents in a decentralized cyber-physical system (CPS), which combines an advanced architecture of graph attention neural networks (CAT-GNN) with blockchain technologies. The proposed approach aims to enhance the security, reliability, and fault tolerance of interactions between agents through dynamic behavioral anomaly analysis using CAT-GNN, capable of detecting complex spatio-temporal dependencies in agent behavior. The calculated anomaly score is used for adaptive adjustment of the trust level in agents, directly influencing access decisions to critical resources within the distributed system. Simulation experiments have demonstrated that the CAT-GNN detector outperforms the baseline STAD-GNN model in key metrics such as Accuracy, Fl-score, and ROC-AUC, showing high stability and precision in detecting malicious behavior while varying the number of agents and the proportion of malicious participants. The introduction of a dynamic trust mechanism significantly increased the proportion of successfully completed tasks from 63 to 82 %, while simultaneously reducing errors from over 18 to 8 %. The method relies on the integration of machine learning and distributed ledger protocols, ensuring transparency, immutability, and flexibility in access management. This comprehensive mechanism effectively counters internal and external threats, meeting modern security requirements of industrial and IoT systems. The proposed method is capable of effective scalability and adaptation to changing conditions of cyber-physical systems, confirming its high practical value and promising potential for broad application in critical infrastructures, industry, and transportation networks.

Keywords: anomalies in cyber-physical systems, graph neural networks, blockchain, NFT, spatio-temporal analysis, trusted interaction, distributed access control, machine learning, cybersecurity

pp. 319—333

For citation:
Petrenko V. I., Najajra M. Kh., Tebueva F. B., Pronin V. I. Distributed Access Control Method for Trusted Interaction of Robotic Agents in a Decentralized Cyber-Physical Environment, Programmnaya Ingeneria, 2026, vol. 17, no. 6, pp. 319—333. DOI: 10.17587/prin.17.319-333.

References:

1. Salimi S., Keramat F., Queralta J. P., Westerlund T. A customizable conflict resolution and attribute-based access control framework for multi-robot systems, Journal of Systems Architecture, 2025, vol. 168, article 103528. DOI: 10.1016/j.sysarc.2025.103528.
2. Pavlov A. S., Svistunov N. Yu., Petrenko V. I. et al. Access control system for information resources of swarm robotic systems under conditions of embedded malicious agents, Informatizatsiya i svyaz. 2022, no. 5, pp. 121—130. DOI: 10.34219/2078-8320-202213-5-121-130 (in Russian).
3. Feng X., Yuan Z. A Trust Evaluation Mechanism Based on Autoencoder Clustering Algorithm for Edge Device Access of IoT, Computers, Materials and Continua, 2024, vol. 78, no. 2, рр. 1881—1895. DOI: 10.32604/cmc.2023.047243.
4. Wang W., Liu Z., Xue L. et al. Malicious vehicle detection scheme based on UAV and vehicle cooperative authentication in vehicular networks, Computer Networks, 2025, vol. 258, article 111037; DOI: 10.1016/j.comnet.2025.111037.
5. Wang W., Liu Z., Zhang S., Liu G. Trust Score-Based Malicious Vehicle Detection Scheme in Vehicular Network Environments, Computers, Materials and Continua, 2024, vol. 81, no. 2, pp. 2517—2545. DOI: 10.32604/cmc.2024.055184.
6. Grillo A., Carpin S., Recchiuto C. T., Sgorbissa A. Trust as a metric for auction-based task assignment in a cooperative team of robots with heterogeneous capabilities, Robotics and Autonomous Systems, 2022, vol. 157, article 104266. DOI: 10.1016/j.robot.2022.104266.
7. Khan W. A., Ahmad F., Alanazi S. A. et al. Trust identification through cognitive correlates with emphasizing attention in cloud robotics, Egyptian Informatics Journal, 2022, vol. 23, no. 2, pp. 259—269. DOI: 10.1016/j.eij.2022.01.003.
8. Ivanov I. V. Cognitive interaction environment of robotic system elements for critical object protection, Aerokosmicheskaya tekhnika, vysokie tekhnologii i innovatsii, 2023, vol. 1, pp. 99—101 (in Russian).
9. Dubenko Yu. V. Method of reuse and experience exchange in collective interaction of intelligent agents, Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta, 2022, vol. 18, no. 1, pp. 62—72. DOI: 10.36622/VSTU.2022.18.1.007 (in Russian).
10. Han P., Wu X., Sui A. DTPBFT: A dynamic and highly trusted blockchain consensus algorithm for UAV swarm, Computer Networks, 2024, vol. 250, article 110602. DOI: 10.1016/j.comnet.2024.110602.
11. Xiong R., Xiao Q., Wang Z. et al. Leveraging lightweight blockchain for secure collaborative computing in UAV Ad-Hoc Networks, Computer Networks, 2024, vol. 251, article 110612; DOI: 10.1016/j.comnet.2024.110612.
12. Peelam M. S., Chamola V., Sharma A. K., Chaurasia B. K. Decentralized Trust: NFT and Blockchain-Enabled Evidence System using Fog Computing, Blockchain: Research and Applications, 2025, article 100321. DOI: 10.1016/j.bcra.2025.100321.
13. Petrenko V. I., Tebueva F. B., Struchkov I. V. et al. Trusted interaction method of agents in decentralized cyber-physical environment based on distributed ledger technology, Prikaspiyskiy zhurnal: upravlenie i vysokie tekhnologii, 2023, no. 3 (63), pp. 115—125 (in Russian).
14. Sokhova Z. B., Redko V. G. Model of self-organization of autonomous agents in decentralized environment, Problemy upravleniya, 2021, no. 2, pp. 42—51. DOI: 10.25728/pu.2021.2.4 (in Russian).
15. Petrenko V. I. Enhancing resilience of mobile cyber-physical systems functioning in spatially distributed tasks using deep multi-agent reinforcement learning, Perspektivy nauki, 2021, no. 3 (138), pp. 164—169. (in Russian).
16. Ivanov S. V., Lozovsky V. V., Savelev I. V. Methodology for distributed decentralized management of heterogeneous UAV groups based on hierarchical clustering algorithms, Voprosy oboronnoy tekh-niki. Seriya 16: Tekhnicheskiye sredstva protivodeystviya terrorizmu, 2024, no. 3—4 (189—190), pp. 3—10 (in Russian).
17. Zhu C., Zhu X., Qin T. Joint trajectory and incentive optimization for privacy-preserving UAV crowdsensing via multi-agent federated reinforcement learning,
Internet of Things, 2025, vol. 33, article 101689. DOI: 10.1016/j.iot.2025.101689.
18. Nie S., Ren J., Wu R. et al. Zero-Trust Access Control Mechanism Based on Blockchain and Inner-Product Encryption in the Internet of Things in a 6G Environment, Sensors, 2025, vol. 25, article 550. DOI: 10.3390/s25020550.
19. Canonico R., Lista F., Navarro A. et al. Threat detection in reconfigurable Cyber-Physical Systems through Spatio-Temporal Anomaly Detection using graph attention network, Computers & Security, 2025, vol. 156, article 104509. DOI: 10.1016/j.cose.2025.104509.
20. Saheed Y. K., Omole A. I., Sabit M. O. GA-mADAM-IIoT: A new lightweight threats detection in the industrial IoT via genetic algorithm with attention mechanism and LSTM on multivariate time series sensor data, Sensors International, 2025, vol. 6, article 100297. DOI: 10.1016/j.sintl.2024.100297.