Less is More: Revisiting Gaussian Mechanism for Differential Privacy

06/04/2023
by   Tianxi Ji, et al.
0

In this paper, we identify that the classic Gaussian mechanism and its variants for differential privacy all suffer from the curse of full-rank covariance matrices, and hence the expected accuracy losses of these mechanisms applied to high dimensional query results, e.g., in ℝ^M, all increase linearly with M. To lift this curse, we design a Rank-1 Singular Multivariate Gaussian Mechanism (R1SMG). It achieves (ϵ,δ)-DP on query results in ℝ^M by perturbing the results with noise following a singular multivariate Gaussian distribution, whose covariance matrix is a randomly generated rank-1 positive semi-definite matrix. In contrast, the classic Gaussian mechanism and its variants all consider deterministic full-rank covariance matrices. Our idea is motivated by a clue from Dwork et al.'s work on Gaussian mechanism that has been ignored in the literature: when projecting multivariate Gaussian noise with a full-rank covariance matrix onto a set of orthonormal basis in ℝ^M, only the coefficient of a single basis can contribute to the privacy guarantee. This paper makes the following technical contributions. (i) R1SMG achieves (ϵ,δ)-DP guarantee on query results in ℝ^M, while the magnitude of the additive noise decreases with M. Therefore, less is more, i.e., less amount of noise is able to sanitize higher dimensional query results. When M→∞, the expected accuracy loss converges to 2(Δ_2f)^2/ϵ, where Δ_2f is the l_2 sensitivity of the query function f. (ii) Compared with other mechanisms, R1SMG is less likely to generate noise with large magnitude that overwhelms the query results, because the kurtosis and skewness of the nondeterministic accuracy loss introduced by R1SMG is larger than that introduced by other mechanisms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/30/2021

Improved Matrix Gaussian Mechanism for Differential Privacy

The wide deployment of machine learning in recent years gives rise to a ...
research
11/27/2019

Reviewing and Improving the Gaussian Mechanism for Differential Privacy

Differential privacy provides a rigorous framework to quantify data priv...
research
01/02/2018

MVG Mechanism: Differential Privacy under Matrix-Valued Query

Differential privacy mechanism design has traditionally been tailored fo...
research
02/26/2018

A Differential Privacy Mechanism Design Under Matrix-Valued Query

Traditionally, differential privacy mechanism design has been tailored f...
research
06/29/2023

Private Covariance Approximation and Eigenvalue-Gap Bounds for Complex Gaussian Perturbations

We consider the problem of approximating a d × d covariance matrix M wit...
research
05/14/2023

An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions

Noisy marginals are a common form of confidentiality-protecting data rel...

Please sign up or login with your details

Forgot password? Click here to reset