Use of Federated Learning in Iiot (Industrial Internet of Things) Security
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P112Keywords:
Federated Learning (FL), Industrial Internet of Things (IIoT), Cyber-Physical Systems (CPS), Intrusion Detection Systems (IDS), Privacy-Preserving Machine LearningAbstract
Federated learning (FL) is a distributed machine learning paradigm that enables devices or edge nodes to collaboratively train a global model without sharing raw data. This enhances privacy and reduces communication overhead. As Industrial Internet of Things (IloT) systems expand across manufacturing, energy, and logistics, security has become critical. Centralized learning approaches struggle with privacy risks, latency, and single points of failure. This article explores the application of FL to strengthen cyber-physical system (CPS) security in IIoT. We present a framework for threat detection, anomaly recognition, and intrusion prevention that utilizes lightweight models, secure aggregation, and differential privacy for resource-constrained industrial devices. Experiments on a simulated smart-factory testbed show that our approach achieves accuracy comparable to centralized methods while maintaining data locality and resilience. We also analyze trade-offs, challenges, and future directions for deploying FL in real-global lloT environments
References
[1] Wikipedia contributors. (2025, August). Industrial internet of things. In Wikipedia. Retrieved September 7, 2025, from https://en.wikipedia.org/wiki/Industrial_internet_of_things
[2] ArXiv contributors. (2023, June 5). Federated deep learning for intrusion detection in IoT networks [Preprint]. arXiv. https://arxiv.org/abs/2306.02715
[3] Wikipedia contributors. (2025, August). Federated learning. In Wikipedia. Retrieved September 7, 2025, from https://en.wikipedia.org/wiki/Federated_learning
[4] Potharaju, R., & Farooq, M. (2022). Securing Internet of Things devices with federated learning: A privacy-preserving approach for distributed intrusion detection. CMC—Computers, Materials & Continua, 83(3), 893–908. https://www.techscience.com/cmc/v83n3/61057/html
[5] McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273–1282. arXiv preprint arXiv:1602.05629
[6] Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated Learning: Strategies for Improving Communication Efficiency. arXiv preprint arXiv:1610.05492. arXiv
[7] Sattler, F., Müller, K.-R., & Samek, W. (2019). Clustered federated learning: Model-agnostic distributed multi-task optimization under privacy constraints. arXiv preprint arXiv:1910.01991
[8] “Operational Technology,” Wikipedia. Retrieved September 7, 2025, from https://en.wikipedia.org/wiki/Operational_technology
[9] Duque Anton, S., Kanoor, S., Fraunholz, D., & Schotten, H. D. (2019). Evaluation of machine learning-based anomaly detection algorithms on an industrial Modbus/TCP data set. arXiv. https://arxiv.org/abs/1905.11757
[10] “Intrusion Detection System,” Wikipedia. Retrieved September 7, 2025, from https://en.wikipedia.org/wiki/Intrusion_detection_system
[11] Duque Anton, S., Sinha, S., & Schotten, H. D. (2019). Anomaly-based intrusion detection in industrial data with SVM and random forests. arXiv. https://arxiv.org/abs/1907.10374
[12] Ali, A., Husain, M., & Hans, P. (2025, May 21). Federated Learning-Enhanced Blockchain Framework for Privacy-Preserving Intrusion Detection in Industrial IoT [Preprint]. arXiv. Retrieved from https://arxiv.org/abs/2505.15376 arXiv
[13] Evaluation of federated intrusion detection in smart manufacturing industries: FLDID: Federated Learning Enabled Deep Intrusion Detection in Smart Manufacturing Industries. PubMed. Retrieved from https://pubmed.ncbi.nlm.nih.gov/36433569/ PubMed
[14] Chatterjee, S., & Hanawal, M. K. (2021, June 25). Federated Learning for Intrusion Detection in IoT Security: A Hybrid Ensemble Approach [Preprint]. arXiv. Retrieved from https://arxiv.org/abs/2106.15349 arXiv
[15] Sarhan, M., Lo, W. W., Layeghy, S., & Portmann, M. (2022, April 8). HBFL: A Hierarchical Blockchain-based Federated Learning Framework for a Collaborative IoT Intrusion Detection [Preprint]. arXiv. Retrieved from https://arxiv.org/abs/2204.04254
[16] Federated learning in intrusion detection: advancements, applications, and future directions. Cluster Computing. Retrieved from https://link.springer.com/article/10.1007/s10586-025-05325-w
[17] Federated Learning-Based Intrusion Detection in IoT Networks: Performance Evaluation and Data Scaling Study. MDPI. Retrieved from https://www.mdpi.com/2224-2708/14/4/78.
