Exploration of New Techniques for Securing Iot Data in Healthcare

The Internet of Medical Things (IoMT) has improved remote monitoring, diagnosis, and timely intervention in modern healthcare, but it has also exposed sensitive patient data to interception, unauthorized access, spoofing, denial-of-service attacks, and data tampering. This paper presents a hybrid security model for healthcare IoT in which lightweight cryptography protects device-level communication, machine-learning-based intrusion detection identifies malicious traffic, blockchain preserves integrity and decentralized access control, federated learning enables collaborative model training without sharing raw data, and homomorphic encryption supports secure computation over encrypted records. The proposed algorithm follows a layered workflow of data acquisition, lightweight encryption, edge-level anomaly detection, blockchain verification, federated parameter aggregation, and privacy-preserving cloud analytics. Experimental validation shows that the proposed model achieves 98.5% detection accuracy, 120 ms average latency, and a security score of 9.5/10, outperforming two baseline models with lower accuracy (91.2% and 89.7%), higher latency (150 ms and 180 ms), and lower security levels (7.2 and 6.8). The results indicate that combining decentralized storage, intelligent threat detection, and privacy-preserving learning provides a practical and scalable solution for securing IoT data in healthcare environments

Cloud computing · Cryptography · Data sharing · Encryption · Homomorphic encryption · Internet of Things · Intrusion detection system · Scalability · Workflow · Blockchain Technology Applications and Security · Internet of Things and AI · IoT and Edge/Fog Computing