What question did this study set out to answer?

This research aims to develop a secure distributed machine learning pipeline to protect healthcare data while ensuring effective anomaly detection.

April 12, 2026Open Access

Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems

Key Points

This research aims to develop a secure distributed machine learning pipeline to protect healthcare data while ensuring effective anomaly detection.
Developed a federated optimization and split learning framework for EMR data.
Implemented robust aggregation techniques to counteract poisoned updates.
Utilized differential privacy and secure aggregation for enhanced data protection.
Applied multimodal fusion with temporal consistency and cross-layer alignment for improved detection accuracy.
Conducted experiments on IoT and EMR datasets to validate efficacy.
Achieved accuracy of 0.942 on IoT data and 0.931 on EMR data, with 0.953 in a combined setting.
F1-scores reached 0.921 for IoT, 0.908 for EMR, and 0.932 overall.
Notable performance with AUROC up to 0.961 and AUPRC up to 0.947, surpassing deep learning baselines by margins of +0.025 to +0.033.
Demonstrated robustness with accuracy decrement of 0.953 to 0.879 under 30% client poisoning.
Reduced detection latency to 5.9 time steps compared to 7.8 for the best deep learning baseline.

Abstract

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.

Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems

Key Points

Abstract

Cite This Study