Shuffled Check-in: Privacy Amplification towards Practical Distributed Learning. (arXiv:2206.03151v1 [cs.LG])

Recent studies of distributed computation with formal privacy guarantees,
such as differentially private (DP) federated learning, leverage random
sampling of clients in each round (privacy amplification by subsampling) to
achieve satisfactory levels of privacy. Achieving this however requires strong
assumptions which may not hold in practice, including precise and uniform
subsampling of clients, and a highly trusted aggregator to process clients'
data. In this paper, we explore a more practical protocol, shuffled check-in,
to resolve the aforementioned issues. The protocol …

amplification distributed lg privacy