A Design Framework for Epsilon-Private Data Disclosure

09/03/2020
by   Amirreza Zamani, et al.
0

In this paper, we study a stochastic disclosure control problem using information-theoretic methods. The useful data to be disclosed depend on private data that should be protected. Thus, we design a privacy mechanism to produce new data which maximizes the disclosed information about the useful data under a strong χ^2-privacy criterion. For sufficiently small leakage, the privacy mechanism design problem can be geometrically studied in the space of probability distributions by a local approximation of the mutual information. By using methods from Euclidean information geometry, the original highly challenging optimization problem can be reduced to a problem of finding the principal right-singular vector of a matrix, which characterizes the optimal privacy mechanism. In two extensions we first consider a noisy disclosure channel and then we look for a mechanism which finds U based on observing X, maximizing the mutual information between U and Y while satisfying the privacy criterion on U and Z under the Markov chain (Z,Y)-X-U.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/15/2021

Data Disclosure with Non-zero Leakage and Non-invertible Leakage Matrix

We study a statistical signal processing privacy problem, where an agent...
research
12/23/2022

On the Privacy-Utility Trade-off With and Without Direct Access to the Private Data

We study an information theoretic privacy mechanism design problem for t...
research
09/16/2023

New Privacy Mechanism Design With Direct Access to the Private Data

The design of a statistical signal processing privacy problem is studied...
research
02/04/2020

The Privacy Funnel from the viewpoint of Local Differential Privacy

We consider a database X⃗ = (X_1,...,X_n) containing the data of n users...
research
03/22/2020

Invariant Rationalization

Selective rationalization improves neural network interpretability by id...
research
11/28/2022

Multi-User Privacy Mechanism Design with Non-zero Leakage

A privacy mechanism design problem is studied through the lens of inform...
research
08/11/2020

Channel Leakage, Information-Theoretic Limitations of Obfuscation, and Optimal Privacy Mask Design for Streaming Data

In this paper, we first introduce the notion of channel leakage as the m...

Please sign up or login with your details

Forgot password? Click here to reset