| dc.description.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 (FL), 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 by Wibawa, using a single
key for homomorphic encryption, our proposed solution is a practical implementation
of a preprint by Ma Jing et. al. 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 FL
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 robust model performance, as demonstrated by consistent
metrics including validation accuracy, precision, f1-score, and recall. | |
