GRU-based Federated Learning for Privacy-Preserving Intrusion Detection in SDN-Enabled IoT Networks

Authors

  • Zaid Ali Alsarray Department of Intelligent Medical System, University of Information Technology and Communication, Baghdad, Iraq.

Conventional security measures have become ineffective against advanced cyber threats due substantial attack surface resulting from the quick growth of Internet of Things (IoT) devices. Software-Defined Networking (SDN) allows centralized control, yet it also engenders privacy issues and complicates scalability. This paper proposes a privacy-preserving Intrusion Detection System (IDS) by integrating Software-Defined Networking (SDN) with a Gated Recurrent Unit (GRU)-based Federated Learning (FL) framework. The proposed SDN-FL-GRU model is different from centralized approaches because it lets distributed IoT nodes work together to train a global intrusion detection model without sharing raw data. It does this by using the FedAvg algorithm to combine the data in an efficient way. Testing the proposed framework on the CICIDS2017dataset shows that it can accurately detect complex attacks while keeping data private, with a detection accuracy of 93.4% and an F1-score of 92.8%. The results obtained indicate that the GRU-based approach outperforms traditional distributed models regarding convergence speed and effectiveness in resource-constrained edge environments.

Keywords:

Federated Learning, Intrusion Detection System, Software-Defined Networking, Gated Recurrent

[1] Adam, M. (2024). Federated Learning for IoT : Applications , Trends , Taxonomy , Challenges , Current Solutions ,. IEEE Open Journal of the Communications Society, 5(October), 7842–7877. https://doi.org/10.1109/OJCOMS.2024.3506214

[2] Ahmadvand, H., Lal, C., Hemmati, H., Sookhak, M., & Member, S. (2023). Privacy-Preserving and Security in SDN-Based IoT : A Survey. 11(May).

[3] Ali, M., Hu, Y., & Li, J. (2025). Federated Learning Augmented Cybersecurity for SDN-Based Aeronautical Communication Network.

[4] Andishmand, R., Mohammdi, H., & Mostafavi, S. (2023). Detection and Analysis of DDoS Attacks in Software-defined Networks.

[5] Chetouane, A., & Karoui, K. (2025). New Continual Federated Learning System for Intrusion Detection in SDN-Based Edge Computing. Concurrency and Computation: Practice and Experience, 37(2), e8332. https://doi.org/https://doi.org/10.1002/cpe.8332

[6] Firdaus, A., Zaki, F., Hanif, H., Aqil, N., & Badrul, N. (2025). Transformer-based tokenization for IoT traf fi c classi fi cation across diverse network environments. 1–31. https://doi.org/10.7717/peerj-cs.3126

[7] Gubbi, J., Buyya, R., & Marusic, S. (2023). Internet of Things ( IoT ): A Vision , Architectural Elements , and Future Directions. 1, 1–19.

[8] Hamad, N. A., Azmi, K., & Bakar, A. B. U. (2025). Systematic Analysis of Federated Learning Approaches for Intrusion Detection in the Internet of Things Environment. IEEE Access, 13(May), 95410–95444. https://doi.org/10.1109/ACCESS.2025.3574672

[9] Harchi, A. (2025). SDN-Cloud Incident Detection & Response with Segmented Federated Learning for the IoT. 5(2), 671–684.

[10] Humayun, M., Tariq, N., Alfayad, M., Zakwan, M., Alwakid, G., & Assiri, M. (2024). Securing the Internet of Things in Artificial Intelligence Era : A Comprehensive Survey. February.

[11] Javeed, D., Shahid, M., Adil, M., & Kumar, P. (2024). Ad Hoc Networks A federated learning-based zero trust intrusion detection system for Internet of Things. Ad Hoc Networks, 162(March), 103540. https://doi.org/10.1016/j.adhoc.2024.103540

[12] Ji, Z., Cui, Y., Guo, Y., & Shen, G. (2025). Towards saturation attack detection in SDN : a multi-edge representation learning-based method.

[13] Khan, L. U., Saad, W., Han, Z., & Hossain, E. (2021). Federated Learning for Internet of Things : Recent Advances , Taxonomy , and Open Challenges. 1–30.

[14] Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021). Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges. IEEE Communications Surveys & Tutorials, 23(3), 1759–1799. https://doi.org/10.1109/COMST.2021.3090430

[15] Kim, T., & Lin, J. (2024). A Survey on Heterogeneity Taxonomy , Security and Privacy Preservation in the Integration of IoT , Wireless Sensor Networks.

[16] Kreutz, D., Ramos, F. M. V, Verissimo, P., Rothenberg, C. E., Azodolmolky, S., Member, S., & Uhlig, S. (2015). Software-Defined Networking : A Comprehensive Survey. 1–49.

[17] Mcmahan, H. B., & Ramage, D. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. 54.

[18] Networks, M. S., Alkhamisi, A., & Katib, I. (2024). Federated Learning-Based Security Attack Detection for.

[19] Pastorek, A., Pastorek, A., & Tundis, A. (2025). Navigating the landscape of IoT security and associated risks in critical infrastructures. July 2024. https://doi.org/10.1145/3664476.3669979

[20] Raza, M., Saeed, M. J., & Sattar, M. A. (2024). Federated Learning for Privacy-Preserving Intrusion Detection in Software-Defined Networks. IEEE Access, 12(April), 69551–69567. https://doi.org/10.1109/ACCESS.2024.3395997

[21] Reis, M. J. C. S. (2025). Scalable Intrusion Detection in IoT Networks via Property Testing and Federated Edge AI. IEEE Access, 13(August), 153244–153262. https://doi.org/10.1109/ACCESS.2025.3603937

[22] S, B. B. (2025). Federated learning in intrusion detection : advancements , applications , and future directions. https://doi.org/10.1007/s10586-025-05325-w

[23] Sharma, N. (2025). A survey on IoT security : challenges and their solutions using machine learning and blockchain technology. In Cluster Computing. Springer US. https://doi.org/10.1007/s10586-025-05208-0

[24] Tom, A. K., Khraisat, A., Jan, T., Nguyen, T. D., & Alazab, A. (2025). Survey of Federated Learning for Cyber Threat Intelligence in Industrial IoT : Techniques , Applications and Deployment Models. 1–25.

[25] Vyas, A., Lin, P.-C., Hwang, R.-H., & Tripathi, M. (2024). Privacy-Preserving Federated Learning for Intrusion Detection in IoT Environments: A Survey. IEEE Access, 12, 127018–127050. https://doi.org/10.1109/ACCESS.2024.3454211

[26] Waheed, S., Hanif, S., Hafeez, R., Sharif, M. I., Siddique, K., & Akhtar, Z. (2024). A Comprehensive Survey on Applications , Challenges , Threats and Solutions in IoT Environment and Architecture. https://doi.org/10.3844/jcssp.2024.310.332

[27] Zhang, H., Ye, J., Huang, W., Liu, X., & Gu, J. (2025). Survey of federated learning in intrusion detection. Journal of Parallel and Distributed Computing, 195, 104976. https://doi.org/https://doi.org/10.1016/j.jpdc.2024.104976

GRU-based Federated Learning for Privacy-Preserving Intrusion Detection in SDN-Enabled IoT Networks. (2026). Journal Port Science Research, 9(2), 405-413. https://doi.org/10.36371/mtjfbw62

License

Copyright (c) 2026 Journal Port Science Research

Creative Commons License

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

How to Cite

GRU-based Federated Learning for Privacy-Preserving Intrusion Detection in SDN-Enabled IoT Networks. (2026). Journal Port Science Research, 9(2), 405-413. https://doi.org/10.36371/mtjfbw62