OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols

TL;DR

OLYMPIA is a simulation framework designed to evaluate the scalability and performance of secure aggregation protocols in federated learning environments with many participants.

Contribution

It introduces an embedded DSL and simulation framework for empirical evaluation of secure protocols, enabling comparison of their scalability.

Findings

First empirical comparison of secure aggregation protocols' end-to-end times

OLYMPIA is open source and facilitates protocol evaluation at scale

Supports high-dimensional models with thousands to millions of participants

Abstract

Recent secure aggregation protocols enable privacy-preserving federated learning for high-dimensional models among thousands or even millions of participants. Due to the scale of these use cases, however, end-to-end empirical evaluation of these protocols is impossible. We present OLYMPIA, a framework for empirical evaluation of secure protocols via simulation. OLYMPIA. provides an embedded domain-specific language for defining protocols, and a simulation framework for evaluating their performance. We implement several recent secure aggregation protocols using OLYMPIA, and perform the first empirical comparison of their end-to-end running times. We release OLYMPIA as open source.