Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning. (arXiv:2304.03841v1 [cs.CR])

Federated learning introduces a novel approach to training machine learning
(ML) models on distributed data while preserving user's data privacy. This is
done by distributing the model to clients to perform training on their local
data and computing the final model at a central server. To prevent any data
leakage from the local model updates, various works with focus on secure
aggregation for privacy preserving federated learning have been proposed.
Despite their merits, most of the existing protocols still incur …

aggregation clients communication computation computing data data leakage data privacy distributed entities federated learning focus high local machine machine learning novel privacy privacy preserving protocols server training updates