Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learning

arXiv:2402.15111v1 Announce Type: cross
Abstract: Secure aggregation enables federated learning (FL) to perform collaborative training of clients from local gradient updates without exposing raw data. However, existing secure aggregation schemes inevitably perform an expensive fresh setup per round because each client needs to establish fresh input-independent secrets over different rounds. The latest research, Flamingo (S&P 2023), designed a share-transfer-based reusable secret key to support the server continuously performing multiple rounds of aggregation. Nevertheless, the share transfer mechanism it proposed can …

abstract aggregation arxiv authentication client collaborative cs.cr cs.dc cs.lg data federated learning gradient per raw setup training type updates