Distributed DP-Helmet: Scalable Differentially Private Non-interactive Averaging of Single Layers

arXiv:2211.02003v2 Announce Type: replace
Abstract: In this work, we propose two differentially private, non-interactive, distributed learning algorithms in a framework called Distributed DP-Helmet. Our framework is based on what we coin blind averaging: each user locally learns and noises a model and all users then jointly compute the mean of their models via a secure summation protocol. We provide experimental evidence that blind averaging for SVMs and single Softmax-layer (Softmax-SLP) can have a strong utility-privacy tradeoff: we reach an accuracy …

algorithms arxiv blind called compute cs.cr cs.lg distributed framework helmet locally non private single stat.ml work