Estimation Efficiency Under Privacy Constraints

Abstract

We investigate the problem of estimating a random variable $Y\in \mathcal{Y}$ under a privacy constraint dictated by another random variable $X\in \mathcal{X}$, where estimation efficiency and privacy are assessed in terms of two different loss functions. In the discrete case, we use the Hamming loss function and express the corresponding utility-privacy tradeoff in terms of the privacy-constrained guessing probability $h(P_{XY},\epsilon )$, the maximum probability ${\mathsf{P}}_{\mathsf{c}}(Y|Z)$ of correctly guessing $Y$ given an auxiliary random variable $Z\in \mathcal{Z}$, where the maximization is taken over all $P_{Z|Y}$ ensuring that ${\mathsf{P}}_{\mathsf{c}}(X|Z)\le \epsilon$ for a given privacy threshold $\epsilon \ge 0$. We prove that $h(P_{XY},\cdot )$ is concave and piecewise linear, which allows us to derive its expression in closed form for any $\epsilon$ when $X$ and $Y$ are binary. In the non-binary case, we derive $h(P_{XY},\epsilon )$ in the high utility regime (i.e., for sufficiently large values of $\epsilon$) under the assumption that $Z$ takes values in $\mathcal{Y}$. We also analyze the privacy-constrained guessing probability for two binary vector scenarios. When $X$ and $Y$ are continuous random variables, we use the squared-error loss function and express the corresponding utility-privacy tradeoff in terms of $\mathsf{sENSR}(P_{XY},\epsilon )$, which is the smallest normalized minimum mean squared-error (mmse) incurred in estimating $Y$ from its Gaussian perturbation $Z$, such that the mmse of $f(X)$ given $Z$ is within $\epsilon$ of the variance of $f(X)$ for any non-constant real-valued function $f$. We derive tight upper and lower bounds for $\mathsf{sENSR}$ when $Y$ is Gaussian. We also obtain a tight lower bound for $\mathsf{sENSR}(P_{XY},\epsilon )$ for general absolutely continuous random variables when $\epsilon$ is sufficiently small.

To appear in IEEE Transaction on Information Theory

References in corpus (3)

• Utility-Privacy Tradeoff in Databases: An Information-theoretic Approach
• A New Data Processing Inequality and Its Applications in Distributed Source and Channel Coding
• A Simple Method for Obtaining the Maximal Correlation Coefficient and Related Characterizations

Cited by in corpus (9)

• On the Information Bottleneck Problems: Models, Connections, Applications and Information Theoretic Views
• A Design Framework for Strongly ${\chi }^2$-Private Data Disclosure
• Pointwise Maximal Leakage
• On the Lift, Related Privacy Measures, and Applications to Privacy-Utility Tradeoffs
• Extremal Mechanisms for Pointwise Maximal Leakage
• Bottleneck Problems: Information and Estimation-Theoretic View
• Answering Count Queries for Genomic Data with Perfect Privacy
• Private Variable-Length Coding with Zero Leakage
• Information Density Bounds for Privacy