Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning

TL;DR

Flamingo is a novel multi-round secure aggregation system for federated learning that reduces interaction complexity and maintains model accuracy while ensuring privacy of client data.

Contribution

It introduces a multi-round secure aggregation protocol with dropout resilience and local client neighborhood selection, improving efficiency over previous single-round protocols.

Findings

Successfully trains neural networks on MNIST and CIFAR-100 datasets.

Achieves secure aggregation with no loss in model accuracy.

Reduces interaction rounds and runtime compared to prior methods.

Abstract

This paper introduces Flamingo, a system for secure aggregation of data across a large set of clients. In secure aggregation, a server sums up the private inputs of clients and obtains the result without learning anything about the individual inputs beyond what is implied by the final sum. Flamingo focuses on the multi-round setting found in federated learning in which many consecutive summations (averages) of model weights are performed to derive a good model. Previous protocols, such as Bell et al. (CCS '20), have been designed for a single round and are adapted to the federated learning setting by repeating the protocol multiple times. Flamingo eliminates the need for the per-round setup of previous protocols, and has a new lightweight dropout resilience protocol to ensure that if clients leave in the middle of a sum the server can still obtain a meaningful result. Furthermore, Flamingo introduces a new way to locally choose the so-called client neighborhood introduced by Bell et al. These techniques help Flamingo reduce the number of interactions between clients and the server, resulting in a significant reduction in the end-to-end runtime for a full training session over prior work. We implement and evaluate Flamingo and show that it can securely train a neural network on the (Extended) MNIST and CIFAR-100 datasets, and the model converges without a loss in accuracy, compared to a non-private federated learning system.