Identification of the message flow between two subscribers in multi-agent systems based on the analysis of its contextual characteristics

Objectives. The paper examines the problem of improving the accuracy of identifying the message flow between two subscribers in multi-agent systems. This is done by analyzing the contextual characteristics of the overall message flow in the communication channel. Situations may arise during the process of source identification and verification of authenticity in which authentication codes for two or more messages collide. One way to resolve such conflicts is to isolate the message flow between two subscribers by leveraging its unique statistical characteristics which differ from the characteristics of the general message flow within the system. The aim of the paper is to develop a method which reliably identifies the target message flow even in cases of authentication code collisions.

Methods. The contextual characteristics of messages are used, in order to analyze and highlight patterns of agent behavior in the message flow. These characteristics include frequency of sending, message size, timestamps, and historical interaction data. The method involves the formation of statistical characteristics of the message flow between two agents in a multi-agent system, such as skewness and kurtosis, as well as distribution parameters for the number of messages sent between events from the target source along with their classification by means of logistic regression.

Results. During experiments, the method developed has been found to demonstrate a Precision metric value in the range of 0.81–0.85. This is 40–50% higher than existing methods based on the analysis of inter-packet time intervals, indicating that 81–85% of the messages classified as belonging to the target source are actually such. ROC analysis confirmed the high efficiency of the model and acceptable classification quality.

Conclusions. The results of the study show that the use of contextual characteristics and statistical analysis enables the accurate identification of target flows in multi-agent systems with a total number of agents ranging from 70 to 110. This method can be used in low-bandwidth communication channels where it is essential to minimize the size of the transmitted batch header and computational costs associated with authentication procedures.

1. Öztürk G., Saran N., Doğanaksoy A. Modified Attribute-Based Authentication for Multi-Agent Systems. Int. J. Inform. Security Sci. 2023;12(3):1–13. https://doi.org/10.55859/ijiss.1294580

2. Kuleshova E.A., Maruhlenko A.L., Dobritsa V.P., Tanygin M.O., Plugatorev A.V. A variant of the algorithm for generating pseudorandom binary sequences based on the properties of linear cellular automata. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies. 2021;54(2):62–70 (in Russ.). https://doi.org/10.21672/2074-1707.2021.53.1.062-070

3. Tanygin M.O., Kuleshova E.A., Mitrofanov A.V., Gladilina E.U. Increasing the speed of error detection when forming data block chains based on the analysis of the number of hash matches. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies. 2022;1(57):85–93 (in Russ.). https://doi.org/10.54398/2074-1707_2022_1_85

4. Yuan J., Yang J., Zhou S., Wang C. Efficient Group Authentication with Multiple Authentications on Resource-Limited Devices. J. Supercomput. 2025;81:929. https://doi.org/10.1007/s11227-025-07404-6

5. Gopirajan P.V., Mani K. Secure Multi-Authentication using BlockchainTechnology in Cloud based Internet of Things. Telematique. 2022;21(1):6640–6650.

6. Wee A.K., Chekole E.G., Zhou J. Excavating Vulnerabilities Lurking in Multi-Factor Authentication Protocols: A Systematic Security Analysis. arXiv Cornell University. 2024;2407(20459):1–24. https://doi.org/10.48550/arXiv.2407.20459

7. Chenchev I. Framework for Multi-factor Authentication with Dynamically Generated Passwords. In: Arai K. (Ed.). Advances in Information and Communication. FICC 2023. Lecture Notes in Networks and Systems. Springer; 2023. V. 652. P. 563–576. https://doi.org/10.1007/978-3-031-28073-3_39

8. Li H., Han D. Blockchain-assisted secure message authentication with reputation management for VANETs. J. Supercomput. 2023;79(17):19903–19933. https://doi.org/10.1007/s11227-023-05394-x

9. Xu Y., Jian X., Li T., Zou S., Li B. Blockchain-Based Authentication Scheme with an Adaptive Multi-Factor Authentication Strategy. Mobile Inform. Syst. 2023;2023:4764135. https://doi.org/10.1155/2023/4764135

10. Liu J., Mu Q., Che R., et al. Multi-participant quantum anonymous communication based on high-dimensional entangled states. Physica Scripta. 2024;99(9):095109. https://doi.org/10.1088/1402-4896/ad69d9

11. Kuleshova E.A., Tanygin M.O. Study of characteristics of modern generators of pseudorandom sequences. Telekommunikatsii = Telecommunications. 2023;7:28–39 (in Russ.). https://doi.org/10.31044/1684-2588-2023-0-7-28-39

12. Tanygin M.O. Restoring the order of information packets based on hash sequence analysis. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2020;24(1):175–188 (in Russ.).

13. Alamgir N., Negati S., Bright C. SHA-256 Collision Attack with Programmatic SAT. arXiv Cornell University. 2024;2406.20072. https://doi.org/10.48550/arXiv.2406.20072

14. Fang Y.Aresearch on different digital signature schemes. Appl.Comput.Eng. 2023;16(1):27–35. http://doi.org/10.54254/2755-2721/16/20230855

15. Phatangare S., Jadhav S., Kawane S., Holkar P., Gaikwad P. Multi-Level Encryption System using AES and RSAAlgorithms. Int. J. Res. Appl. Sci. Eng. Technol. 2024;15(5):4043–4051. https://doi.org/10.22214/IJRASET.2024.62420

16. Tanygin M.O., Alshaeaa H.Y., Kuleshova E.A. A method of the transmitted blocks information integrity control. Radio Electronics, Computer Science, Control. 2020;1:181–189.

17. Tao M., Li Q., Yu J. Multi-Objective Dynamic Path Planning with Multi-Agent Deep Reinforcement Learning. J. Marin. Sci. Eng. 2025;13(1):20. https://doi.org/10.3390/jmse13010020

18. Morais D., Zuquete A., Mendes A. Adaptive, Multi-Factor Authentication as a Service for Web Applications. In: 2023 7th Cyber Security in Networking Conference (CSNet). 2023. P. 74–80. http://doi.org/10.1109/CSNet59123.2023.10339695

19. Plugatarev A.V. Model for determining the message source by statistical analysis of metadata in an open communication channel. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies. 2022;4(60):30–37 (in Russ.).

20. Dharrao D., Gaikwad P., Gawai S.V., Bongale A.M., Patel K., Singh A. Classifying SMS as spam or ham: Leveraging NLP and machine learning techniques. Int. J. Saf. Secur. Eng. 2024;14(1):289–296. https://doi.org/10.18280/ijsse.140128

21. Placzek B. A Multi-Agent Prediction Method for Data Sampling and Transmission Reduction in Internet of Things Sensor Networks. Sensors. 2023;23(20):8478. https://doi.org/10.3390/s23208478

22. Vedmiediev D., Shapoval N. Text Message Clustering. Electronics and Control Systems. 2023;4(78):16–20.

23. Katwal S., Sharma N., Kumar K. A Deep Learning Approach for Throughput Enhanced Clustering and Spectrally Efficient Resource Allocation in Ultra-Dense Networks. IEEE Trans. Netw. Service Manag. 2025;22(1):582–591. https://doi.org/10.1109/TNSM.2024.3470235

24. Huang X., Zhou S. QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning. IEEE Trans. Mobile Comput. 2023;23(5):4739–4751. https://doi.org/10.1109/TMC.2023.3296726

25. Goloveshkin V.A., Zhukova G.N., Ulyanov M.V., Fomichev M.I. The estimation of the complexity of solving a particular travelling salesman problem by quantile-based measures for skewness and kurtosis. Int. J. Open Inform. Technol. 2016;4(12):7–12 (in Russ.). https://elibrary.ru/xetabh

26. Tanygin M.O., Dobritsa V.P., Mitrofanov A.V., Ahmat Kh.I. Mathematical interpretation of the results of cognitive analysis of network packets metadata. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2023;27(3):66–78 (in Russ.).