Research on Federated Learning-based Intrusion Detection Methods for the Internet of Things

doi:10.12379/j.issn.2096-1057.2026.09.01

Abstract

Abstract: The rapid expansion of the Internet of Things (IoT) has given rise to pressing cybersecurity challenges. Traditional centralized intrusion detection approaches encounter difficulties in balancing model performance and data privacy protection. Federated learning enables collaborative model training without sharing raw data among participants, which provides a novel paradigm for IoT intrusion detection. This paper presents a systematic review of federated learning-driven IoT intrusion detection methods. It first introduces the fundamental background and typical architectures of this research field. It then categorizes existing methods into three types: federated machine learning, federated deep learning, and federated reinforcement learning, and analyzes the characteristics, application scenarios,and existing limitations of each category. This paper further summarizes common enhancement mechanisms, cutting-edge technologies, public datasets, and evaluation indicators used in this field. Finally, this paper discusses key open challenges, including label scarcity, Non-Independent and Identically Distributed (Non-IID) data, federated multimodal large models and security enhancement, and proposes potential future research directions. This review can provide a useful technical reference for subsequent research and practical applications in this field.

Key words: federated learning, internet of things intrusion detection, federated intrusion detection, federated deep learning, federated reinforcement learning

摘要： 随着物联网（Internet of Things，IoT）的快速发展，其网络安全问题日益凸显。传统集中式入侵检测系统难以兼顾安全性与隐私保护，而联邦学习通过在不共享原始数据的前提下实现多节点协同建模，为物联网入侵检测提供了新的技术路径。本文围绕联邦学习驱动的物联网入侵检测方法展开系统性综述。首先介绍物联网入侵检测的基本原理及联邦物联网入侵检测系统的典型架构；随后从方法层面对现有研究进行分类梳理，总结基于联邦机器学习、联邦深度学习及联邦强化学习的物联网入侵检测方法，分析各类方法的核心特点、适用场景与挑战；继而概述了联邦学习驱动的面向物联网的联邦学习入侵检测系统（Federated Learning?based Intrusion Detection System for Internet of Things，FL-IoT-IDS）的联邦增强机制和前沿研究技术，并总结常用物联网入侵检测数据集及评估指标。最后，针对当前研究中普遍存在的关键问题，从低标注依赖建模、非独立同分布（Non-Independent and Identically Distributed，Non-IID）数据适配、联邦多模态大模型以及联邦学习安全性增强等方向探讨未来研究趋势。本文旨在为联邦学习在物联网入侵检测领域的研究与应用提供技术参考。

关键词: 联邦学习, 物联网入侵检测, 联邦入侵检测, 联邦深度学习, 联邦强化学习

CLC Number:

TP309

陈良臣, 傅德印, 蒋子龙, 刘宝旭, 卢志刚, 姜政伟. 联邦学习驱动的物联网入侵检测方法研究综述[J]. 信息安全研究, 2026, 12(9): 780-788.

References

[1] 班云飞. 基于深度学习的物联网入侵检测研究[D]. 贵州贵阳：贵州大学，2025. [2] 陈良臣，傅德印，刘宝旭，等. 基于机器学习的网络未知攻击检测方法研究综述[J]. 信息安全研究，2025，11（9）：807-813. [3] Gueriani A, Kheddar H, Mazari A C. Deep reinforcement learning for intrusion detection in IoT: a survey[C]//2023 2nd International Conference on Electronics, Energy and Measurement (IC2EM). Piscataway, NJ: IEEE, 2023, 1: 1-7. [4] 陈良臣，傅德印，刘宝旭，等. 基于联邦学习的网络协同入侵检测方法研究综述[J]. 信息安全研究，2026，12（6）：526-532. [5] Ruzafa-Alcázar P, Fernández-Saura P, Mármol-Campos E, et al. Intrusion detection based on privacy-preserving federated learning for the industrial IoT[J]. IEEE Transactions on Industrial Informatics, 2023, 19(2): 1145-1154. [6] Bhavsar MH, Bekele YB, Roy K, et al. FL-IDS: Federated Learning-Based Intrusion Detection System Using Edge Devices for Transportation IoT[J]. IEEE Access, 2024, 12(3): 52215-52226. [7] Hossain MA, Saif S, Islam MS. A novel federated learning approach for IoT botnet intrusion detection using SHAP-based knowledge distillation[EB/OL]. 2025[2026-01-13]. https://link.springer.com/article/10.1007/s40747-025-02001-9. [8] Devine M, Ardakani SP, Al-Khafajiy M, et al. Federated Machine Learning to Enable Intrusion Detection Systems in IoT Networks [J]. Electronics, 2025, 14(6): 1176. [9] Dong T, Qiu H, Lu J L, Qiu M K, Fan C. Towards fast network intrusion detection based on efficiency-preserving federated learning[EB/OL]. 2021[2026-01-13]. https://ieeexplore.ieee.org/document/9644849%5Breference:0%5D%5Breference:1%5D. [10] Hajj S, Azar J, Abdo JB, et al. Cross-layer federated learning for lightweight IoT intrusion detection systems[J]. Sensors, 2023, 23(16): 7038. [11] Anaissi A. A personalized federated learning algorithm for one-class support vector machine: An application in anomaly detection[C]. International Conference on Computational Science (ICCS). Cham: Springer, 2022. [12] Cámara XS, Flores JL, Arellano C, et al. Clustered federated learning architecture for network anomaly detection in large scale heterogeneous IoT networks[J]. Computers & Security, 2023, 131: 103299. [13] 尹春勇，王珊. 基于联邦学习和注意力机制的物联网入侵检测模型[J]. 信息安全研究，2025，11（9）：788-796. [14] Anwar RW, Abrar M, Salam A, et al. Federated learning with LSTM for intrusion detection in IoT-based wireless sensor networks: A multi-dataset analysis[J]. PeerJ Computer Science, 2025, 11: e2751. [15] 成翔，匡苗苗，张佳乐，等. 面向物联网系统的APT攻击活动预测方法[J]. 信息安全学报，2025，10（4）：176-189. [16] Javeed D, Saeed MS, Ahmad M, et al. A federated learning-based zero trust intrusion detection system for Internet of Things[J]. Ad Hoc Networks, 2024, 162: 103540. [17] Ogunniye BG, Prinetto P. Federated learning-based intrusion detection system for the Internet of Things using unsupervised and supervised deep learning models[J]. Cyber Security and Applications, 2025, 3: 100068. [18] Jahromi A N, Karimipour H, Dehghantanha A. Deep federated learning-based cyber-attack detection in industrial control systems[EB/OL]. 2021[2026-01-13]. https://ieeexplore.ieee.org/abstract/document/9647838. [19] Janati ME, Amine H, El Mohajir A, et al. Fed-ANIDS: Federated learning for anomaly-based network intrusion detection systems[J]. Expert Systems With Applications, 2023, 234: 121000. [20] Ramya SP, Kanimozhi KV, Sreesubha S. Federated GAN-augmented explainable deep learning framework for IoT intrusion detection[C]. Proceedings of the International Conference on Data Intelligence and Computing Things (IDCIoT). Piscataway, NJ: IEEE, 2026: 1557-1563. [21] Zhao H, Liu L, Fan F, et al. An adaptive federated learning intrusion detection system based on generative adversarial networks under the Internet of Things[C]. Proceedings of the 2024 Asia Conference on Algorithms, Computing and Machine Learning. Piscataway, NJ: IEEE, 2024: 1-6. [22] Bouzeraib W, Ghenai A, Zeghib N. Enhancing IoT intrusion detection systems through horizontal federated learning and optimized WGAN-GP[J]. IEEE Access, 2025, 13: 45059-45076. [23] Muthuswamy HN, Suthagar MS, Natarajan V. Hybrid transformer and XGBoost model for federated IoT intrusion detection[C]. Proceedings of the IEEE 5th International Conference on Artificial Intelligence and Computing (ICAIC). Piscataway, NJ: IEEE, 2026: 1-6. [24] Reddy B, Manohar S, Thanuja P. Federated transformer model for edge-level intrusion detection systems[C]. 2025 5th International Conference on Electronics, Communication and Signal Processing (ICECMSN). Piscataway, NJ: IEEE, 2025: 1395-1401. [25] AlTfaily AF, Ghalmane Z, Brahmia Z. Graph-based federated learning approach for intrusion detection in IoT networks[J]. Scientific Reports, 2025, 15: 41264. [26] Ma X, Hu J, Liang S, et al. Federated learning and resource-aware graph neural network for intrusion detection in 6G-IoT driven healthcare system[J]. IEEE Internet of Things Journal, 2026, 13(5):7749-7761. [27] Sagar N, Shambharkar P G, Mehra P S. GNN?FedGAN: A GNN-enhanced federated GAN for anomaly detection in IoT security[C]//Artificial Intelligence and Sustainable Innovation. Boca Raton, FL: CRC Press, 2026:195-203. [28] AlHayan A, Al-Muhtadi J. Federated learning-powered real-time behavioral intrusion detection leveraging LSTM, attention, GANs, and large language models[J]. Scientific Reports, 2026, 16: 10172. [29] Radoglou-Grammatikis P. AI4FIDS: Multimodal federated intrusion detection[J]. IEEE Transactions on Emerging Topics in Computing, 2025. DOI: 10.1109/TETC.2025.3562346. [30] Ahmad HB, Gao H, Latif N, et al. FedMamba: Robust multimodal federated intrusion detection for heterogeneous IoT systems[J]. Internet of Things, 2026: 101877. [31] Aryo H, Rahardjo B. Fed-CALiBER: Federated lightweight BERT intrusion detection on CAN bus protocol in autonomous vehicle[J]. IEEE Access, 2025, 13: 172384-172401. [32] Khan IA, Raza I, Pi D, et al. Fed-Inforce-Fusion: A federated reinforcement-based fusion model for security and privacy protection of IoMT networks against cyber-attacks[J]. Information Fusion, 2024, 101: 102002. [33] Rabaie B, Amine D. SFEDRL-IDS: Secure federated deep reinforcement learning-based intrusion detection system for agricultural Internet of Things[J]. Cluster Computing, 2025, 28: 403. [34] Al-Maslamani NA, Sahin CB, Abdallah M, et al. Toward secure federated learning for IoT using DRL-enabled reputation mechanism[J]. IEEE Internet of Things Journal, 2022, 9(21): 21971-21983. [35] Mrabet H, El-Azouzi Z, Brik B. Advancing security and trust in WSNs: A federated multi-agent deep reinforcement learning approach[J]. IEEE Transactions on Consumer Electronics, 2024, 70(4): 6909-6918. [36] Vemuru S, Sethi K, Mishra D, et al. Federated reinforcement learning based intrusion detection system using dynamic attention mechanism[J]. Journal of Information Security and Applications, 2023, 78: 103608. [37] Al-Maslamani NA, Abdallah M, Sahin BC. Reputation-aware multi-agent DRL for secure hierarchical federated learning in IoT[J]. IEEE Open Journal of the Communications Society, 2023, 4: 1274-1284. [38] Attaullah HM, Basheer S, Ehsan M. Multi-agent federated edge learning for UAV-IDS in smart city IoT environment[J]. IEEE Transactions on Consumer Electronics, 2026, 72(2):3988-3995.