Securing IoMT with Federated Learning: A Hybrid Deep Learning and Ensemble-Based Intrusion Detection Framework
Abstract
Abstract The rapid proliferation of Internet of Medical Things (IoMT) devices has significantly enhanced healthcare connectivity while simultaneously increasing exposure to sophisticated cyber threats such as distributed denial-of-service attacks, malware propagation, and data exfiltration. Traditional centralized intrusion detection systems (IDS) are increasingly unsuitable for IoMT environments due to strict privacy regulations, decentralized data ownership, device heterogeneity, and communication constraints. To address these challenges, this paper proposes a privacy-preserving federated intrusion detection framework that integrates a hybrid Deep Neural Network (DNN) and XGBoost model within a federated learning (FL) architecture. Unlike conventional FedAvg-based approaches, the proposed method leverages the complementary strengths of deep feature extraction and gradient-boosting classification, enhanced by differential privacy, secure aggregation, and robust aggregation techniques to mitigate adversarial poisoning attacks. The problem is formally modeled as distributed empirical risk minimization under non-independent and identically distributed (non-IID) client data, with convergence behavior analyzed under bounded gradient variance and client drift. Extensive experiments conducted on WUSTL-EHMS-2020, UNSW-NB15, and BoT-IoT datasets demonstrate that the proposed framework achieves detection accuracy of up to 91.4% with F1-scores exceeding 90%, closely approaching…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.