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

02/20/2023
by   Ivoline C. Ngong, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/23/2021

Sparsified Secure Aggregation for Privacy-Preserving Federated Learning

Secure aggregation is a popular protocol in privacy-preserving federated...
research
11/10/2022

Secure Aggregation Is Not All You Need: Mitigating Privacy Attacks with Noise Tolerance in Federated Learning

Federated learning is a collaborative method that aims to preserve data ...
research
06/19/2019

Scalable and Differentially Private Distributed Aggregation in the Shuffled Model

Federated learning promises to make machine learning feasible on distrib...
research
05/24/2022

Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

We propose Byzantine-robust federated learning protocols with nearly opt...
research
11/14/2016

Practical Secure Aggregation for Federated Learning on User-Held Data

Secure Aggregation protocols allow a collection of mutually distrust par...
research
10/05/2021

Secure Aggregation for Buffered Asynchronous Federated Learning

Federated learning (FL) typically relies on synchronous training, which ...
research
08/12/2021

SAFE: Secure Aggregation with Failover and Encryption

We propose and experimentally evaluate a novel secure aggregation algori...

Please sign up or login with your details

Forgot password? Click here to reset