Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Moudoud, H.; Houda, Z. Abou El; Brik, B.
Advancing Privacy and Fairness in Healthcare Using Federated Edge Learning and Blockchain Article de journal
Dans: IEEE Internet of Things Journal, vol. 12, no 22, p. 46129–46137, 2025, ISSN: 23274662 (ISSN).
Résumé | Liens | BibTeX | Étiquettes: Artificial intelligence algorithms, Artificial intelligence techniques, Block-chain, Blockchain, cancer diagnosis, Diagnosis, Distributed computer systems, Federated edge learning, Health care, Healthcare, Healthcare systems, Internet of medical thing, Internet of Medical Things (IoMT), Learning systems, Medical computing, Medical data, Network security, Privacy, Sensitive data
@article{moudoudAdvancingPrivacyFairness2025,
title = {Advancing Privacy and Fairness in Healthcare Using Federated Edge Learning and Blockchain},
author = {H. Moudoud and Z. Abou El Houda and B. Brik},
url = {https://www.scopus.com/pages/publications/105012264671?origin=resultslist},
doi = {10.1109/JIOT.2025.3589179},
issn = {23274662 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Internet of Things Journal},
volume = {12},
number = {22},
pages = {46129–46137},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {artificial intelligence (AI) has revolutionized many fields, including healthcare. The adoption of AI techniques in critical healthcare tasks, such as cancer diagnosis, holds great promise for revolutionizing the healthcare system. AI algorithms can be trained on vast datasets to recognize patterns, detect anomalies, and provide accurate assessments. However, the lack of realistic and up-to-date medical data poses a significant challenge to the widespread adoption of AI techniques. Additionally, privacy concerns surrounding sensitive medical data, particularly patient health records (PHRs), hinder data sharing among healthcare practitioners. This article aims to address these challenges by proposing a novel framework, entitled SecureMed, that uses federated learning (FL) and Blockchain to preserve privacy in the healthcare system. In particular, SecureMed consists of: 1) a novel distributed architecture that enables secure collaboration among multiple mobile edge computing (MEC)-based Internet of Medical Things (IoMT) devices, while ensuring the privacy of healthcare systems; 2) a fairness-aware FL solution to ensure that model performance is balanced across all participating healthcare institutions, addressing the issue of imbalanced data contributions; 3) a secure multiparty computation (SMPC) protocol to ensure secure aggregation of local model updates; and 4) a blockchain-based reputation model for collaborative FL training. The proposed framework leverages smart contracts to ensure trustworthiness, decentralization, and transparency in the FL process. The experimental results using the CIC IoMT dataset 2024 highlight the promising potential of SecureMed in revolutionizing healthcare systems. © 2014 IEEE.},
keywords = {Artificial intelligence algorithms, Artificial intelligence techniques, Block-chain, Blockchain, cancer diagnosis, Diagnosis, Distributed computer systems, Federated edge learning, Health care, Healthcare, Healthcare systems, Internet of medical thing, Internet of Medical Things (IoMT), Learning systems, Medical computing, Medical data, Network security, Privacy, Sensitive data},
pubstate = {published},
tppubtype = {article}
}
artificial intelligence (AI) has revolutionized many fields, including healthcare. The adoption of AI techniques in critical healthcare tasks, such as cancer diagnosis, holds great promise for revolutionizing the healthcare system. AI algorithms can be trained on vast datasets to recognize patterns, detect anomalies, and provide accurate assessments. However, the lack of realistic and up-to-date medical data poses a significant challenge to the widespread adoption of AI techniques. Additionally, privacy concerns surrounding sensitive medical data, particularly patient health records (PHRs), hinder data sharing among healthcare practitioners. This article aims to address these challenges by proposing a novel framework, entitled SecureMed, that uses federated learning (FL) and Blockchain to preserve privacy in the healthcare system. In particular, SecureMed consists of: 1) a novel distributed architecture that enables secure collaboration among multiple mobile edge computing (MEC)-based Internet of Medical Things (IoMT) devices, while ensuring the privacy of healthcare systems; 2) a fairness-aware FL solution to ensure that model performance is balanced across all participating healthcare institutions, addressing the issue of imbalanced data contributions; 3) a secure multiparty computation (SMPC) protocol to ensure secure aggregation of local model updates; and 4) a blockchain-based reputation model for collaborative FL training. The proposed framework leverages smart contracts to ensure trustworthiness, decentralization, and transparency in the FL process. The experimental results using the CIC IoMT dataset 2024 highlight the promising potential of SecureMed in revolutionizing healthcare systems. © 2014 IEEE.