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

arXiv:2308.09883v3 Announce Type: replace-cross
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 …

abstract aggregation applications arxiv beyond cs.cr cs.lg data federated learning inputs paper replace server set type