Secure Aggregation for Clustered Federated Learning With Passive Adversaries

Clustered federated learning is a popular paradigm to tackle data heterogeneity in federated learning, by training personalized models for groups of users with similar data distributions. A critical challenge is to protect the privacy of individual user updates, as the latter can reveal extensive information about sensitive local datasets. To do so, a recent promising approach is information-theoretic secure aggregation, where parties learn the aggregate (sum) of user updates, but no further information is revealed about the individual updates. In this work, we present the first single-server secure aggregation framework in the context of clustered federated learning, to learn the aggregate of user updates for any clustering of users, but without learning any information about the local updates or cluster identities. Our framework can achieve linear communication complexity under formal information-theoretic privacy guarantees, while providing key trade-offs between communication and computation complexity, adversary tolerance, and resilience to user dropouts.