The Relative Gaussian Mechanism and its Application to Private Gradient Descent

arXiv:2308.15250v2 Announce Type: replace
Abstract: The Gaussian Mechanism (GM), which consists in adding Gaussian noise to a vector-valued query before releasing it, is a standard privacy protection mechanism. In particular, given that the query respects some L2 sensitivity property (the L2 distance between outputs on any two neighboring inputs is bounded), GM guarantees R\'enyi Differential Privacy (RDP). Unfortunately, precisely bounding the L2 sensitivity can be hard, thus leading to loose privacy bounds. In this work, we consider a Relative L2 …

abstract application arxiv cs.cr cs.lg gradient inputs math.oc noise privacy property protection query sensitivity standard type vector