Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation. (arXiv:2202.10618v1 [cs.CR])

Computing the noisy sum of real-valued vectors is an important primitive in
differentially private learning and statistics. In private federated learning
applications, these vectors are held by client devices, leading to a
distributed summation problem. Standard Secure Multiparty Computation (SMC)
protocols for this problem are susceptible to poisoning attacks, where a client
may have a large influence on the sum, without being detected.

In this work, we propose a poisoning-robust private summation protocol in the
multiple-server setting, recently studied in …

applications arxiv data distributed distributed data