A Three-Stage Federated Distillation Framework for Robust Intrusion Detection in Heterogeneous IoT/Edge Networks
Open Access
- 25 August 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (17) , 3810
Abstract
Internet of Things(IoT)/edge intrusion-detection systems operate on distributed traffic and system-state data whose distributions vary across gateways, services, and attack conditions. We study a server-assisted federated setting in which a teacher reference is fitted from a permitted server-accessible training pool and explicitly distinguish this simulation assumption from fully decentralized deployment. The proposed framework evaluates progressive local training through boundary stabilization, confidence-weighted decision distillation, representation alignment, and validation-quality-aware aggregation. The evaluation uses a leakage-controlled protocol: server and client validation subsets are held out before federated training, update quality and early stopping use validation data only, and the final-test split is evaluated once. Results on NSL-KDD, CIC-IDS2017, Edge-IIoTset, and the ToN-IoT network dataset show competitive primary performance and stronger robustness in several severe label-skew settings. On the Telemetry of Things(ToN-IoT) with Dirichlet alpha = 0.1, the proposed method achieves 91.46 ± 5.54 F1, compared with 53.73 ± 49.00 for FedAvg and 53.77 ± 48.92 for FedProx. The results do not establish universal superiority or a universally optimal stage order: competing methods remain stronger in selected stable and attack-shift settings. The framework is therefore presented as a bounded, server-assisted robustness-oriented training strategy for heterogeneous IoT/edge intrusion detection.Keywords
Funding Information
- Youth Innovation Team Project of the Shaanxi Provincial Department of Education (2030100790)
- Shaanxi Provincial Social Science Foundation Project (2024J280)
- Open Project of the Shanxi Key Laboratory of Data Factor Innovation and Economic Decision Analysis (2025-KF-02)
- 2024 State Grid Henan Cooperation Project (5217L0240004)
- Shaanxi Natural Science Basic Research Program (2026JC-YBQN-0756)
This publication has 18 references indexed in Scilit:
- Robust federated intrusion detection under statistical heterogeneityComputer Networks, 2025
- Federated learning in intrusion detection: advancements, applications, and future directionsCluster Computing, 2025
- Federated learning with self-updating server parameters for smart home intrusion detection in Non-IID environmentsExpert Systems with Applications, 2024
- A comprehensive survey of Federated Intrusion Detection Systems: Techniques, challenges and solutionsComputer Science Review, 2024
- Edge-IIoTset: A New Comprehensive Realistic Cyber Security Dataset of IoT and IIoT Applications for Centralized and Federated LearningIEEE Access, 2022
- Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental AnalysisIEEE Access, 2021
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- Intrusion Detection for Wireless Edge Networks Based on Federated LearningIEEE Access, 2020
- TON_IoT Telemetry Dataset: A New Generation Dataset of IoT and IIoT for Data-Driven Intrusion Detection SystemsIEEE Access, 2020
- Towards the development of realistic botnet dataset in the Internet of Things for network forensic analytics: Bot-IoT datasetFuture Generation Computer Systems, 2019