$\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning

TL;DR

This paper introduces $ extsf{OPA}$, a one-shot secure aggregation protocol for federated learning that reduces communication rounds, simplifies dropout handling, and outperforms existing solutions in practicality.

Contribution

The paper presents $ extsf{OPA}$, a novel one-round secure aggregation protocol based on various cryptographic assumptions, enabling efficient federated learning with minimal client-server interaction.

Findings

$ extsf{OPA}$ achieves asymptotic efficiency improvements over prior protocols.

Experimental results show $ extsf{OPA}$ outperforms state-of-the-art solutions in practical benchmarks.

Built classifiers demonstrate applicability to real-world datasets like MNIST and CIFAR.

Abstract

Our work aims to minimize interaction in secure computation due to the high cost and challenges associated with communication rounds, particularly in scenarios with many clients. In this work, we revisit the problem of secure aggregation in the single-server setting where a single evaluation server can securely aggregate client-held individual inputs. Our key contribution is the introduction of One-shot Private Aggregation ($\mathsf{OPA}$) where clients speak only once (or even choose not to speak) per aggregation evaluation. Since each client communicates only once per aggregation, this simplifies managing dropouts and dynamic participation, contrasting with multi-round protocols and aligning with plaintext secure aggregation, where clients interact only once. We construct $\mathsf{OPA}$ based on LWR, LWE, class groups, DCR and demonstrate applications to privacy-preserving Federated Learning (FL) where clients \emph{speak once}. This is a sharp departure from prior multi-round FL protocols whose study was initiated by Bonawitz et al. (CCS, 2017). Moreover, unlike the YOSO (You Only Speak Once) model for general secure computation, $\mathsf{OPA}$ eliminates complex committee selection protocols to achieve adaptive security. Beyond asymptotic improvements, $\mathsf{OPA}$ is practical, outperforming state-of-the-art solutions. We benchmark logistic regression classifiers for two datasets, while also building an MLP classifier to train on MNIST, CIFAR-10, and CIFAR-100 datasets. We build two flavors of $\caps$ (1) from (threshold) key homomorphic PRF and (2) from seed homomorphic PRG and secret sharing.