FL-GCN-LG-Trust: A Federated Graph-Based Trust Framework for Secure Cluster Optimization and Intrusion Detection in Underwater Wireless Sensor Networks

Authors

  • Kourosh Daniel Seifi Departmant of Computer Engineering, IAU, Science and Research Branch, Tehran, Iran.
  • Parvaneh Asghari Departmant of Computer Engineering, Shahed University, Tehran, Iran.
  • Hamid Haj Seyyed Javadi * Departmant of Computer Engineering, Shahed University, Tehran, Iran.
  • Mohammad Hadi Alaeiyan Departmant of Computer engineering, K. N. Toosi University of Technology, Tehran, Iran.

https://doi.org/10.48314/tsc.v1i2.36

Abstract

This paper presents Federated Learning (FL)-Graph Convolutional Network (GCN)-Light Gradient (LG)-Trust, a federated, graph-based trust framework designed for anomaly detection and cluster optimization in Underwater Wireless Sensor Networks (UWSNs). The proposed architecture utilizes GCNs to compute both local and global trust scores, thereby improving the assessment of node reliability. By integrating FL, the framework facilitates collaborative training without centralizing data, thereby preserving privacy across distributed nodes. Additionally, a trust-aware cluster head selection protocol is developed to balance energy efficiency and network security. To evaluate its effectiveness, the framework is tested against traditional trust models under various attack scenarios, including data tampering, physical breaches, and environmental manipulations. Experimental results demonstrate that FL-GCN-LG-trust consistently outperforms existing models in detection accuracy, with significant improvements in true positive rates and F1-scores. Further simulations show that adjusting trust parameters and optimizing graph edge weights enhance system robustness while maintaining low communication overhead. The comparative analysis confirms that FL-GCN-LG-Trust provides not only improved detection performance but also scalable deployment potential in real-world underwater sensor networks. By combining FL techniques with trust modeling, the framework offers a secure, energy-efficient, and privacy-preserving solution for next-generation underwater network infrastructures.

Keywords:

Underwater wireless sensor networks, Federated learning, Graph convolutional networks, Trust management, Attack detection

References

  1. [1] Akyildiz, I. F., Pompili, D., & Melodia, T. (2005). Underwater acoustic sensor networks: Research challenges. Ad hoc networks, 3(3), 257–279. https://doi.org/10.1016/j.adhoc.2005.01.004
  2. [2] Tian, W., Zhao, Y., Hou, R., Dong, M., Ota, K., Zeng, D., & Zhang, J. (2023). A centralized control-based clustering scheme for energy efficiency in underwater acoustic sensor networks. IEEE transactions on green communications and networking, 7(2), 668–679. https://doi.org/10.1109/TGCN.2023.3249208
  3. [3] Riveros-Rojas, G. J., Cespedes-Sanchez, P. P., Pinto-Roa, D. P., & Legal-Ayala, H. (2024). Energy-and-blocking-aware routing and device assignment in software-defined networking—a MILP and genetic algorithm approach. Mathematical and computational applications, 29(2), 18. https://doi.org/10.3390/mca29020018
  4. [4] Zhu, R., Boukerche, A., Long, L., & Yang, Q. (2024). Design guidelines on trust management for underwater wireless sensor networks. IEEE communications surveys & tutorials, 26(4), 2547–2576. https://doi.org/10.1109/COMST.2024.3389728
  5. [5] Sreekantha, B., & Shaila, K. (2024). Exploring the synergy of machine learning algorithms in wireless sensor networks: A comprehensive survey. Intelligent electrical systems and industrial automation (pp. 45–57). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-97-6806-6_4
  6. [6] Al-Shamaileh, M., Anthony, P., & Charters, S. (2024). Agent-based trust and reputation model in smart IoT environments. Technologies, 12(11), 208. https://doi.org/10.3390/technologies12110208
  7. [7] Babu, G. R., Vaishali, K., Madhuri, K. H., Deepika, E., & Chowdary, K. K. (2024). Trusted net: A lightweight cluster-based trust sensing system for IoT networks. Journal of science & technology, 9(4), 74–83. https://doi.org/10.46243/jst.2024.v9.i4.pp74-83
  8. [8] Jiang, B., Zhou, R., Luo, F., Cui, X., Liu, Y., & Song, H. (2024). Hybrid trust model for identifying malicious attacks in underwater acoustic sensor network. IEEE sensors journal, 24(16), 26743–26754. https://doi.org/10.1109/JSEN.2024.3424252
  9. [9] Lenard, T., Collen, A., Benyahya, M., Nijdam, N. A., & Genge, B. (2023). Exploring trust modeling and management techniques in the context of distributed wireless networks: A literature review. IEEE access, 11, 106803–106832. https://doi.org/10.1109/ACCESS.2023.3320945
  10. [10] Zhu, R., Boukerche, A., & Yang, Q. (2023). Towards a trusted channel energy-aware routing algorithm for underwater sensor networks. Proceedings of the 19th ACM international symposium on QOS and security for wireless and mobile networks (pp. 47–51). New York, NY, USA: Association for computing machinery. https://doi.org/10.1145/3616391.3622777
  11. [11] Liao, H. (2025). E-commerce live-streaming platform and decision support system based on fuzzy association rule mining. International journal of computational intelligence systems, 18(1), 41. https://doi.org/10.1007/s44196-025-00744-4
  12. [12] Zhu, R., Boukerche, A., Feng, L., & Yang, Q. (2023). A trust management-based secure routing protocol with AUV-aided path repairing for underwater acoustic sensor networks. Ad hoc networks, 149, 103212. https://doi.org/10.1016/j.adhoc.2023.103212
  13. [13] Jiang, Z., Xing, F., Tan, Y., & Tong, F. (2024). A discrete-time markov chains cloud-based trust management approach model for underwater wireless sensor networks. 2024 international conference on artificial intelligence of things and systems (AIOTSYS) (pp. 1–7). IEEE. https://doi.org/10.1109/AIoTSys63104.2024.10780741
  14. [14] Liu, C., Ye, J., An, F., & Jiang, W. (2024). An adaptive trust evaluation model for detecting abnormal nodes in underwater acoustic sensor networks. Sensors, 24(9), 2880. https://doi.org/10.3390/s24092880
  15. [15] He, Y., Han, G., Li, A., Taleb, T., Wang, C., & Yu, H. (2023). A federated deep reinforcement learning-based trust model in underwater acoustic sensor networks. IEEE transactions on mobile computing, 23(5), 5150–5161. https://doi.org/10.1109/TMC.2023.3301825
  16. [16] Kalghatgi, H., Dhawle, M., & Raut, U. (2023). Defense techniques against spoofing attacks in wireless sensor networks. Materials today: Proceedings. https://doi.org/10.1016/j.matpr.2023.03.357
  17. [17] Huan, X., Miao, K., Chen, W., Jia, P., & Hu, H. (2024). Kerra: An internet of things wireless key generation resistant to replay attacks. IEEE internet of things journal, 11(17), 29035–29048. https://doi.org/10.1109/JIOT.2024.3406702
  18. [18] Yan, J., Guan, X., Yang, X., Chen, C., & Luo, X. (2025). A survey on integration design of localization, communication and control for underwater acoustic sensor networks. IEEE internet of things journal, 12(6), 6300–6324. https://doi.org/10.1109/JIOT.2025.3525482
  19. [19] Campagnaro, F., Steinmetz, F., & Renner, B. C. (2023). Survey on low-cost underwater sensor networks: from niche applications to everyday use. Journal of marine science and engineering, 11(1), 125. https://doi.org/10.3390/jmse11010125
  20. [20] Zayed, M. M., Shokair, M., Ghallab, R., & others. (2025). Modeling and analysis of underwater optical wireless communication channels. International journal of engineering and applied sciences-october 6 university, 2(1), 32–45. https://doi.org/10.21608/ijeasou.2025.349270.1040
  21. [21] Theocharidis, T., & Kavallieratou, E. (2025). Underwater communication technologies: A review. Telecommunication systems, 88(2), 54. https://doi.org/10.1007/s11235-025-01279-x
  22. [22] Shah, S., Munir, A., Salam, A., Ullah, F., Amin, F., AlSalman, H., & Javeed, Q. (2024). A dynamic trust evaluation and update model using advance decision tree for underwater wireless sensor networks. Scientific reports, 14(1), 22393. https://doi.org/10.1038/s41598-024-72775-4
  23. [23] Jain, S., & Verma, R. K. (2024). A taxonomy and survey on grid-based routing protocols designed for wireless sensor networks. ACM computing surveys, 56(8), 1–41. https://doi.org/10.1145/3653315
  24. [24] Zhang, M., Feng, R., Zhang, H., & Su, Y. (2023). A recommendation management defense mechanism based on trust model in underwater acoustic sensor networks. Future generation computer systems, 145, 466–477. https://doi.org/10.1016/j.future.2023.03.043
  25. [25] Gupta, S., & Singh, N. P. (2024). Underwater wireless sensor networks: A review of routing protocols, taxonomy, and future directions. The journal of supercomputing, 80(4), 5163–5196. https://doi.org/10.1007/s11227-023-05646-w
  26. [26] Bharany, S., Sharma, S., Alsharabi, N., Tag Eldin, E., & Ghamry, N. A. (2023). Energy-efficient clustering protocol for underwater wireless sensor networks using optimized glowworm swarm optimization. Frontiers in marine science, 10, 1117787. https://doi.org/10.3389/fmars.2023.1117787
  27. [27] Zukarnain, Z. A., Amodu, O. A., Wenting, C., & Bukar, U. A. (2023). A survey of Sybil attack countermeasures in underwater sensor and acoustic networks. IEEE access, 11, 64518–64543. https://doi.org/10.1109/ACCESS.2023.3288330
  28. [28] Khan, M. U., Otero, P., & Aamir, M. (2024). An energy efficient clustering routing protocol based on arithmetic progression for underwater acoustic sensor networks. IEEE sensors journal, 24(5), 6964–6975. https://doi.org/10.1109/JSEN.2024.3354252
  29. [29] Kanavalli, A., Chaudhari, S. S., & others. (2024). Trust-based data fusion and machine learning for underwater sensor networks. 2024 4th Asian conference on innovation in technology (Asiancon) (pp. 1–6). IEEE. https://doi.org/10.1109/ASIANCON62057.2024.10838202
  30. [30] Uyan, O. G., Akbas, A., & Gungor, V. C. (2023). Machine learning approaches for underwater sensor network parameter prediction. Ad hoc networks, 144, 103139. https://doi.org/10.1016/j.adhoc.2023.103139
  31. [31] Rakesh, S., Praveen, R. V. S., Ramkumar Prabhu, M., Chauhan, A., Pal, S., & Kalra, G. (2024). Graph convolutional neural networks for attack detection in wireless sensor networks security. https://dx.doi.org/10.2139/ssrn.5091230
  32. [32] Tiwari, A., & Darbari, M. (2025). Emerging trends in computer science and its application. CRC Press Boca Raton, FL, USA. https://dx.doi.org/10.1201/9781003606635
  33. [33] Kumar, M., Goyal, N., Qaisi, R. M. A., Najim, M., & Gupta, S. K. (2025). Joint trust-based detection and signature-based authentication technique for secure localization in underwater wireless sensor network. Multimedia tools and applications, 84(31), 37845–37864. https://doi.org/10.1007/s11042-025-20683-8
  34. [34] Mir, M., & Trik, M. (2025). A novel intrusion detection framework for industrial IoT: GCN-GRU architecture optimized with ant colony optimization. Computers and electrical engineering, 126, 110541. https://doi.org/10.1016/j.compeleceng.2025.110541
  35. [35] Le, M., Hoang, D. T., Nguyen, D. N., Pham, Q. V., & Hwang, W. J. (2023). Wirelessly powered federated learning networks: Joint power transfer, data sensing, model training, and resource allocation. IEEE internet of things journal, 11(21), 34093–34107. https://doi.org/10.1109/JIOT.2023.3324151

Published

2025-04-21

Issue

Vol. 1 No. 2 (2025): Transactions on Soft Computing

Section

Articles

How to Cite

Daniel Seifi, K., Asghari, P., Haj Seyyed Javadi, H., & Alaeiyan, M. H. (2025). FL-GCN-LG-Trust: A Federated Graph-Based Trust Framework for Secure Cluster Optimization and Intrusion Detection in Underwater Wireless Sensor Networks. Transactions on Soft Computing , 1(2). https://doi.org/10.48314/tsc.v1i2.36