Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

FedSMOTE-DP: Privacy-Aware Federated Ensemble Learning for Intrusion Detection in IoMT Networks.

Theyab Alsolami^1,2, Mohammad Ilyas¹

¹Department of Electrical Engineering and Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, FL 33431, USA.

Sensors (Basel, Switzerland)

|March 14, 2026

Summary

Related Concept Videos

Masking and Demasking Agents

Masking and Demasking Agents

EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Estimation of gut microbiome motif associated with active tuberculosis - A case control study.

Bioinformation·2026

Same author

ML-FSID-FIS: A Multi-Level Feature Selection and Fuzzy Inference System for Intrusion Detection in IoMT.

Sensors (Basel, Switzerland)·2026

Same author

Generation of biologically responsive colon-like intestinal tissue patches from human induced pluripotent stem cells using a rapid co-differentiation platform.

Stem cell research & therapy·2026

Same author

A Prospective Analysis of Maternal and Fetal Outcomes in Term Pregnancies Complicated by Oligohydramnios at Bundelkhand Medical College.

Journal of pharmacy & bioallied sciences·2026

Same author

Enhancing Tuberculosis Diagnosis and Treatment Monitoring: Evaluating Ki67 and HLA-DR Biomarkers Via Point-of-Care Testing and Comparative Analysis of Flow Cytometry Versus ELISA in Whole Blood Samples.

Journal of pharmacy & bioallied sciences·2026

Same author

Health Literacy and Psychological Well-Being of Occupational Drivers in Central India.

Journal of pharmacy & bioallied sciences·2026

This study introduces FedEnsemble-DP, a privacy-preserving framework for detecting intrusions in the Internet of Medical Things (IoMT). It achieves high accuracy even with strong privacy settings, enhancing IoMT cybersecurity.

Area of Science:

Cybersecurity
Healthcare Technology
Machine Learning

Background:

The Internet of Medical Things (IoMT) offers transformative healthcare potential but is vulnerable to cyber threats like intrusion and data exfiltration.
Centralized intrusion detection systems (IDSs) pose privacy and scalability challenges due to data aggregation requirements.

Purpose of the Study:

To propose FedEnsemble-DP, a privacy-aware Federated Learning (FL) framework for decentralized intrusion detection in IoMT networks.
To evaluate the effectiveness of integrating data balancing techniques with Differential Privacy (DP) and Secure Aggregation.

Main Methods:

Developed FedEnsemble-DP, a Federated Learning framework incorporating three data balancing scenarios: Raw Imbalanced, Local SMOTE, and Centralized SMOTE.
Integrated Differential Privacy (DP) with calibrated noise and Secure Aggregation mechanisms.

Keywords:

Federated Learning (FL)Internet of Medical Things (IoMT)cybersecurity differential privacy ensemble learning intrusion detection system (IDS)machine learning privacy preservation secure aggregation

Related Experiment Videos

Conducted experiments on WUSTL-EHMS-2020 and CIC-IoMT-2024 datasets under non-IID conditions (Dirichlet α = 0.3).

Main Results:

Models with strong privacy guarantees (ε = 3.0) achieved performance comparable to or exceeding non-private baselines.
Local SMOTE with ε = 3.0 yielded 94.60% accuracy and 0.9598 AUC; Raw Imbalanced with ε = 3.0 achieved 94.50% accuracy and 0.9494 AUC.
Privacy-preserving models (ε = 3.0) surpassed the non-private baseline (93.20% accuracy) in the raw scenario, despite potential instability with Centralized SMOTE.

Conclusions:

Local data balancing combined with calibrated DP noise effectively enhances intrusion detection performance in IoMT networks while preserving data privacy.
The FedEnsemble-DP framework successfully balances security, performance, and data confidentiality requirements in distributed healthcare environments.