Differential privacy has been a de facto privacy standard in defining privacy and handling
privacy preservation. It has had great success in scenarios of local data privacy and …

We develop an advanced approach for extending Gaussian Differential Privacy (GDP) to
general Riemannian manifolds. The concept of GDP stands out as a prominent privacy …

In this paper, we study the differentially private empirical risk minimization problem where
the parameter is constrained to a Riemannian manifold. We introduce a framework for …

A common step in differentially private ({DP}) Riemannian optimization is sampling from the
(tangent) Gaussian distribution as noise needs to be generated in the tangent space to …

In this paper we consider the problem of releasing a Gaussian Differentially Private (GDP)
3D human face. The human face is a complex structure with many features and inherently …

Differential Privacy (DP)[45] has been known as a gold standard for data privacy. On one
hand, it defines pairwise secrets not to be distinguishable with the bound of a predefined …