DeepAI AI Chat
Log In Sign Up

Differential Privacy for Binary Functions via Randomized Graph Colorings

by   Rafael G. L. D'Oliveira, et al.

We present a framework for designing differentially private (DP) mechanisms for binary functions via a graph representation of datasets. Datasets are nodes in the graph and any two neighboring datasets are connected by an edge. The true binary function we want to approximate assigns a value (or true color) to a dataset. Randomized DP mechanisms are then equivalent to randomized colorings of the graph. A key notion we use is that of the boundary of the graph. Any two neighboring datasets assigned a different true color belong to the boundary. Under this framework, we show that fixing the mechanism behavior at the boundary induces a unique optimal mechanism. Moreover, if the mechanism is to have a homogeneous behavior at the boundary, we present a closed expression for the optimal mechanism, which is obtained by means of a pullback operation on the optimal mechanism of a line graph. For balanced mechanisms, not favoring one binary value over another, the optimal (ϵ,δ)-DP mechanism takes a particularly simple form, depending only on the minimum distance to the boundary, on ϵ, and on δ.


page 1

page 2

page 3

page 4


Reviewing and Improving the Gaussian Mechanism for Differential Privacy

Differential privacy provides a rigorous framework to quantify data priv...

A Nearly Instance-optimal Differentially Private Mechanism for Conjunctive Queries

Releasing the result size of conjunctive queries and graph pattern queri...

Differentially Private Multivariate Statistics with an Application to Contingency Table Analysis

Differential privacy (DP) has become a rigorous central concept in priva...

DP-SIPS: A simpler, more scalable mechanism for differentially private partition selection

Partition selection, or set union, is an important primitive in differen...

Differentially Private Sliced Wasserstein Distance

Developing machine learning methods that are privacy preserving is today...

Differentially Private Diffusion Auction: The Single-unit Case

Diffusion auction refers to an emerging paradigm of online marketplace w...

A Unified Characterization of Private Learnability via Graph Theory

We provide a unified framework for characterizing pure and approximate d...