Journal of Analytical and Applied Computer Sciences | Volume 2 Issue 2 | Pages: 22-31 | Doi : 10.67914/jaacs/rsa/2.2/22-31

Research Article

OPEN ACCESS | Published on : 31-Aug-2026

Privacy-Preserving Intrusion Detection in Internet of Things Networks Using Federated Learning and Federated Averaging

• Umar Muhammad Badikko
• Department of Computer Science, Federal University of Kashere, Nigeria.

Peter Buba Zirra
• Department of Computer Science, Federal University of Agriculture, Mubi, Adamawa State, Nigeria.

Abstract

The increasing deployment of Internet of Things (IoT) devices has created significant security and privacy concerns because connected devices continuously generate sensitive network data. Conventional centralized intrusion-detection systems require these data to be transmitted to a central server, potentially exposing confidential information and creating communication and scalability challenges. This study investigated a privacy-preserving intrusion-detection approach based on horizontal Federated Learning (FL), Random Forest (RF), and the Federated Averaging (FedAvg) algorithm. The proposed architecture enables participating IoT devices to retain raw network traffic locally while transmitting model parameters to a central aggregation server. A model-security validation stage was incorporated to assess the trustworthiness of local model parameters before their aggregation into the global model. The Edge-IIoTset cybersecurity dataset was used for model development and evaluation. The dataset contains 2,219,201 samples, 63 original features, a binary attack label, and 14 labelled attack classes, with a reported distribution of 73% normal and 27% attack traffic. Data preprocessing involved feature cleaning, removal of redundant and high-cardinality attributes, elimination of duplicate and erroneous records, and one-hot encoding of categorical variables. Experimental findings showed that the global federated model achieved 99.7% accuracy and an F1-score of 0.90 in the reported binary evaluation. Accuracy across five participating IoT device categories ranged from 99.3% to 99.9%. The results indicate that the federated approach can provide effective intrusion detection while retaining raw data at the edge. Nevertheless, the study identifies data heterogeneity, minority-class detection, computational overhead, and poisoning attacks as continuing challenges. The findings support Federated Learning as a promising architecture for privacy-preserving and scalable IoT intrusion detection.

Keywords

Internet of Things, privacy preservation, Federated Learning, FedAvg, intrusion detection, Random Forest, Edge-IIoTset

References

• Aashmi, R., & Jaya, T. (2022). Intrusion detection using federated learning for computing.

  Almalki, L., Alnahdi, A., & Albalawi, T. (2023). Role-driven clustering of stakeholders: A study of IoT security improvement. Sensors, 23, 5578.

  Bhatnagar, A. (2024). Network intrusion detection system using federated learning. GLIMPSE—Journal of Computer Science, 3(1), 4–9.

  Bhavsar, M., Roy, K., Kelly, J., & Olusola, O. (2023). Anomaly-based intrusion detection system for IoT application. Discover Internet of Things, 3, 1–23. https://doi.org/10.1007/s43926-023-00034-5.

  Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017). Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (pp. 1175–1191).

  Chaurasia, N., Ram, M., Verma, P., Mehta, N., & Bharot, N. (2024). A federated learning approach to network intrusion detection using residual networks in industrial IoT networks. The Journal of Supercomputing, 80, 18326–18346. https://doi.org/10.1007/s11227-024-06153-2.

  Dash, N., Chakravarty, S., & Rath, A. K. (2024). Deep learning model for elevating Internet of Things intrusion detection. International Journal of Electrical and Computer Engineering, 14(5), 5874–5883. https://doi.org/10.11591/ijece.v14i5.pp5874-5883.

  Emmanni, P. S. (2021). Federated learning for cybersecurity in edge and cloud computing. International Journal of Computing and Engineering, 14–25.

  Feng, Z. (2024). Federated learning security threats and defense approaches. Highlights in Science, Engineering and Technology, 85, 121–127.

  Ferrag, M. A., Friha, O., Hamouda, D., Maglara, L., & Janicke, H. (2022). Edge-IIoTset: A new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning. TechRxiv. https://doi.org/10.36227/techrxiv.18857336.v1.

  Marfo, W., Tosh, D. K., & Moore, S. V. (2022). Network anomaly detection using federated learning. In 2022 IEEE Military Communications Conference (MILCOM).

  Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. V. (2021). Federated learning for Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23(3), 1622–1658.

  Rashid, M. M., Khan, S. U., Eusufzai, F., Redwan, M. A., Sabuj, S. R., & Elsharief, M. (2023). A federated learning-based approach for improving intrusion detection in industrial Internet of Things networks.

  Silva, P. R., Vinagre, J., & Gama, J. (2023). Towards federated learning: An overview of methods and applications. WIREs Data Mining and Knowledge Discovery, 13(4), e1486. https://doi.org/10.1002/widm.1486⁠

  Singh, V. K., Tucker, E., & Rath, S. (2024). Federated machine learning-based anomaly detection system for synchrophasor network using heterogeneous data sets. In 2024 IEEE/PES Transmission and Distribution Conference and Exposition (T&D) (pp. 1–5). IEEE. https://doi.org/10.1109/TD47997.2024.10556259.

  Tahri, R., Balouki, Y., Jarrar, A., & Lasbahani, A. (2022). Intrusion detection system using machine learning algorithms. ITM Web of Conferences, 46, 02003. https://doi.org/10.1051/itmconf/20224602003.

  Weinger, B., Kim, J., Sim, A., Nakashima, M., Moustafa, N., & Wu, K. (2022). Enhancing IoT anomaly detection performance for federated learning. Digital Communications and Networks, 8(3), 314–323.

  Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., & Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems, 216, 106775. https://doi.org/10.1016/j.knosys.2021.106775⁠