A Practical Implementation of Medical Privacy-Preserving Federated Learning Using Multi-Key Homomorphic Encryption and Flower Framework

Abstract

The digitization of healthcare data has presented a pressing need to address privacy concerns within the realm of machine learning for healthcare institutions. One promising solution is federated learning, which enables collaborative training of deep machine learning models among medical institutions by sharing model parameters instead of raw data. This study focuses on enhancing an existing privacy-preserving federated learning algorithm for medical data through the utilization of homomorphic encryption, building upon prior research. In contrast to the previous paper, this work is based upon Wibawa, using a single key for HE, our proposed solution is a practical implementation of a preprint with a proposed encryption scheme (xMK-CKKS) for implementing multi-key homomorphic encryption. For this, our work first involves modifying a simple “ring learning with error” RLWE scheme. We then fork a popular federated learning framework for Python where we integrate our own communication process with protocol buffers before we locate and modify the library’s existing training loop in order to further enhance the security of model updates with the multi-key homomorphic encryption scheme. Our experimental evaluations validate that, despite these modifications, our proposed framework maintains a robust model performance, as demonstrated by consistent metrics including validation accuracy, precision, f1-score, and recall.