Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors
This addresses privacy concerns in federated learning for network users, offering a scalable solution without a trusted third party.
The paper tackles the challenge of privacy in federated learning by introducing a new protocol that combines differential privacy with secure aggregation using Learning With Errors, achieving optimal accuracy and scalability to a large number of parties.
Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring their own challenges -- many require a trusted third party or else add too much noise to produce useful models. Recent advances in \emph{secure aggregation} using multiparty computation eliminate the need for a third party, but are computationally expensive especially at scale. We present a new federated learning protocol that leverages a novel differentially private, malicious secure aggregation protocol based on techniques from Learning With Errors. Our protocol outperforms current state-of-the art techniques, and empirical results show that it scales to a large number of parties, with optimal accuracy for any differentially private federated learning scheme.