<p>Performance comparison on IoT dataset.</p>

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 ( at 30% malicious clients) and resilience under severe communication constraints (accuracy 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.

物联网（Internet of Things, IoT）设备与电子病历（Electronic Medical Records, EMR）的融合革新了医疗服务交付模式，但也催生了新型网络攻击漏洞，同时威胁数据机密性与患者安全。传统集中式机器学习入侵检测方法在此领域并不适用，原因包括严苛的隐私监管要求、异构数据源以及单点故障风险。为应对上述挑战，我们提出一种面向网络弹性（cyber-resilient）医疗系统的安全分布式机器学习流水线。该框架将针对敏感电子病历数据的联合优化（federated optimization）与拆分学习（split learning）、用于缓解投毒更新（poisoned updates）的鲁棒聚合（robust aggregation），以及可抵御推理攻击（inference attack）的差分隐私（differential privacy）与安全聚合相结合。通过针对物联网流量的时序一致性正则化（temporal consistency regularization）与用于关联电子病历表征的跨层对比对齐（cross-layer contrastive alignment）实现多模态融合（multimodal fusion），确保在多样化医疗环境中提升异常检测（anomaly detection）性能。在代表性物联网与电子病历数据集上开展的实验表明，所提流水线在物联网数据上的准确率达0.942，电子病历数据上达0.931，联合场景下达0.953，对应的F1分数分别为0.921、0.908与0.932。排序类评估指标进一步验证了其优越性：受试者工作特征曲线下面积（Area Under the Receiver Operating Characteristic Curve, AUROC）最高可达0.961，精确召回曲线下面积（Area Under the Precision-Recall Curve, AUPRC）最高可达0.947，相较主流深度基准模型高出0.025至0.033个百分点。鲁棒性分析显示，在30%恶意客户端参与的投毒攻击场景下，模型性能可实现平滑退化；且在严苛通信约束（更新稀疏化率达90%）下仍保持良好韧性。检测延迟降至平均5.9个时间步长，而表现最优的深度基准模型的检测延迟为7.8个时间步长。上述结果表明，安全分布式流水线可同时实现优异的检测性能与监管合规性，为守护下一代医疗基础设施抵御持续演进的网络威胁提供了切实可行的路径。