Trust-Aware Federated Learning for Privacy-Preserving IoT Intrusion Detection
Open Access
- 9 October 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (20) , 4584
Abstract
The rapid growth of Internet of Things (IoT) networks has increased the need for intrusion detection mechanisms that provide accurate threat detection while preserving privacy, resisting malicious clients, and limiting communication overhead. Existing Federated Learning (FL)-based intrusion detection systems (IDS) remain challenged by heterogeneous non-IID client data, exposure of model updates, adversarial client participation, and frequent model transmission. To address these limitations, this paper proposes FLZT-IDS (Federated Learning with Zero-Trust for Intrusion Detection in IoT). The framework employs gradient-deviation monitoring to mitigate the effects of heterogeneous client updates, while Graph Neural Networks (GNN) and an Attention-based BiLSTM capture relational and temporal attack patterns, respectively. Secure Aggregation with Local Differential Privacy (SALDP) protects transmitted model updates, whereas dynamic trust-based client filtering limits the contribution of potentially malicious participants. An adaptive communication mechanism transmits local updates only when the model change exceeds a predefined threshold, thereby reducing unnecessary communication. Experiments on CICIDS2017 and Edge-IIoTset show that FLZT-IDS achieves 97.8% and 96.2% accuracy, respectively. Compared with FL-IDS, the adaptive communication and trust-filtering mechanisms reduce cumulative communication overhead by more than 30% after 100 communication rounds. Under model-poisoning experiments with 30% malicious clients, FLZT-IDS maintains accuracies of 89.3% on CICIDS2017 and 87.1% on Edge-IIoTset, demonstrating improved robustness under the evaluated adversarial setting.Keywords
Funding Information
- National Natural Science Foundation of China (52577124)
- National Natural Science Foundation of China (52207125)
- Key Research and Development Program of Hunan Province Project (2024JK2040)
- Shaoyang University Doctoral Research Start-up Special Project (25KYQD166)
This publication has 45 references indexed in Scilit:
- SIAD: a low-latency AI-driven software architecture for anomaly detection in industrial IoT environmentsCluster Computing, 2026
- Federated learning based deep learning framework for robust object detection in indoor and outdoor environmentsComputers and Electrical Engineering, 2026
- Enhancing can security with ML-based IDS: Strategies and efficacies against adversarial attacksComputers & Security, 2025
- Machine Learning-Based Attack Detection for the Internet of ThingsFuture Generation Computer Systems, 2024
- Fed-ANIDS: Federated learning for anomaly-based network intrusion detection systemsExpert Systems with Applications, 2023
- An efficient centralized DDoS attack detection approach for Software Defined Internet of ThingsThe Journal of Supercomputing, 2023
- Federated Learning for intrusion detection system: Concepts, challenges and future directionsComputer Communications, 2022
- Attention-Based Bi-LSTM for Anomaly Detection on Time-Series Data2021
- Internet of Things Applications: Opportunities and ThreatsWireless Personal Communications, 2021
- A robust intelligent zero-day cyber-attack detection techniqueComplex & Intelligent Systems, 2021