Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems
PLOS One · 10.04.2026 · 21 (4) · e0343669
DOI: 10.1371/journal.pone.0343669 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.04.2026. Verfasst von Md Iftekhar Monzur Tanvir und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Washington University of Science and Technology, Alexandria, Virginia, United States of America. Hauptthemen laut MEDLINE: Computer Security, Internet of Things, Delivery of Health Care, Privacy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The integration of Internet of Things (IoT) devices and electronic medical records (EMRs) has transformed healthcare delivery but has also created new vulnerabilities to cyberattacks that threaten both data confidentiality and patient safety. Conventional centralized machine learning approaches for intrusion detection are impractical in this domain due to strict privacy regulations, heterogeneous data sources, and the risk of single points of failure. To address these challenges, we propose a secure distributed machine learning pipeline for cyber-resilient healthcare systems. The framework combines federated optimization with split learning for sensitive EMR data, robust aggregation to mitigate poisoned updates, and differential privacy with secure aggregation to protect against inference attacks. Multimodal fusion is enabled through temporal consistency regularization for IoT traffic and cross-layer contrastive alignment to link EMR representations, ensuring improved anomaly detection across diverse healthcare environments. Experiments conducted on representative IoT and EMR datasets demonstrate that the proposed pipeline achieves accuracy of 0.942 on IoT data, 0.931 on EMR data, and 0.953 in the combined setting, with corresponding F1-scores of 0.921, 0.908, and 0.932. Ranking metrics further confirm superiority with AUROC up to 0.961 and AUPRC up to 0.947, outperforming deep baselines by margins of +0.025 to +0.033. Robustness analysis shows graceful degradation under client poisoning ( 0.953 → 0.879 at 30% malicious clients) and resilience under severe communication constraints (accuracy 0.953 → 0.861 at 90% update sparsification). Detection latency is reduced to an average of 5.9 time steps, compared to 7.8 for the strongest deep baseline. These results highlight that secure distributed pipelines can deliver both strong detection capabilities and regulatory compliance, providing a practical path toward safeguarding next-generation healthcare infrastructures against evolving cyber threats.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Information Technology, Washington University of Science and Technology, Alexandria, Virginia, United States of America.
- Department of Computer Science, Campbellsville University, Louisville, Kentucky, United States of America.
- Department of Information Technology, University of the Potomac, Potomac, Washington, D.C., United States of America.
- Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh.
ORCID-Profile: Habibor Rahman Rabby, Kamruddin Nur
Zitieren
APA
Tanvir, M. I. M., Rabby, H. R., Arif, M. H., Nadia, N. Y., & Nur, K. (2026). Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems. PLOS One, 21(4), e0343669. https://doi.org/10.1371/journal.pone.0343669
Vancouver
Tanvir MIM, Rabby HR, Arif MH, Nadia NY, Nur K. Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems. PLOS One. 2026;21(4):e0343669. doi:10.1371/journal.pone.0343669
BibTeX
@article{Tanvir2026,
author = {Tanvir, Md Iftekhar Monzur and Rabby, Habibor Rahman and Arif, Md Habibul and Nadia, Nusrat Yasmin and Nur, Kamruddin},
title = {Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {4},
pages = {e0343669},
doi = {10.1371/journal.pone.0343669}
}
EUVIMED