A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index

09/22/2021
by   Georgios Kaissis, et al.
0

The Gaussian mechanism (GM) represents a universally employed tool for achieving differential privacy (DP), and a large body of work has been devoted to its analysis. We argue that the three prevailing interpretations of the GM, namely (ε, δ)-DP, f-DP and Rényi DP can be expressed by using a single parameter ψ, which we term the sensitivity index. ψ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation. With strong links to the ROC curve and the hypothesis-testing interpretation of DP, ψ offers the practitioner a powerful method for interpreting, comparing and communicating the privacy guarantees of Gaussian mechanisms.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/27/2019

Reviewing and Improving the Gaussian Mechanism for Differential Privacy

Differential privacy provides a rigorous framework to quantify data priv...
10/13/2021

Offset-Symmetric Gaussians for Differential Privacy

The Gaussian distribution is widely used in mechanism design for differe...
10/28/2021

Privacy Preserving Inference on the Ratio of Two Gaussians Using (Weighted) Sums

The ratio of two Gaussians is useful in many contexts of statistical inf...
01/30/2019

Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA

The exponential mechanism is a fundamental tool of Differential Privacy ...
05/23/2019

Elliptical Perturbations for Differential Privacy

We study elliptical distributions in locally convex vector spaces, and d...
10/12/2021

Adjusting Queries to Statistical Procedures Under Differential Privacy

We consider a dataset S held by an agency, and a vector query of interes...
08/02/2021

Privacy-Aware Rejection Sampling

Differential privacy (DP) offers strong theoretical privacy guarantees, ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.