Quantum-Resistant Secure Aggregation for Healthcare Federated Learning

Federated Learning (FL) enables collaborative medical model training without sharing sensitive patient data. However, existing FL systems face increasing security risks from post quantum adversaries and often incur non-negligible computational and communication overhead when encryption is applied. At the same time, training high performance AI models requires large volumes of high quality data, while medical data such as patient information, clinical records, and diagnostic reports are highly sensitive and subject to strict privacy regulations, including HIPAA and GDPR. Traditional centralized machine learning approaches therefore pose significant challenges for cross institutional collaboration in healthcare. To address these limitations, Federated Learning was introduced to allow multiple institutions to jointly train a global model while keeping local data private. Nevertheless, conventional cryptographic mechanisms, such as RSA, are increasingly inadequate for privacy sensitive FL deployments, particularly in the presence of emerging quantum computing threats. Homomorphic encryption, which enables computations to be performed directly on encrypted data, provides an effective solution for preserving data privacy in federated learning systems. This capability allows healthcare institutions to securely perform collaborative model training while remaining compliant with regulatory requirements. Among homomorphic encryption techniques, NTRU, a lattice based cryptographic scheme defined over polynomial rings, offers strong resistance against quantum attacks by relying on the hardness of the Shortest Vector Problem (SVP). Moreover, NTRU supports limited homomorphic operations that are sufficient for secure aggregation in federated learning. In this work, we propose an NTRU enhanced federated learning framework specifically designed for medical and healthcare applications. Experimental results demonstrate that the proposed approach achieves classification performance comparable to standard federated learning, with final accuracy consistently exceeding 0.93. The framework introduces predictable encryption latency on the order of hundreds of milliseconds per training round and a fixed ciphertext communication overhead per client under practical deployment settings. In addition, the proposed system effectively mitigates multiple security threats, including quantum computing attacks, by ensuring robust encryption throughout the training process. By integrating the security and homomorphic properties of NTRU, this study establishes a privacy preserving and quantum resistant federated learning framework that supports the secure, legal, and efficient deployment of AI technologies in healthcare, thereby laying a solid foundation for future intelligent healthcare systems.