A Linear Reduction Method for Local Differential Privacy and Log-lift

TL;DR

This paper introduces a linear method for generating sanitized data that simultaneously achieves local differential privacy and log-lift, improving data utility while protecting sensitive information.

Contribution

The paper proposes a novel linear sanitization scheme that optimally balances privacy and utility by solving linear equations for data transformation.

Findings

The method maintains the original marginal distribution of data.

Non-Markov randomization enhances data utility significantly.

The approach effectively achieves both LDP and log-lift simultaneously.

Abstract

This paper considers the problem of publishing data $X$ while protecting correlated sensitive information $S$. We propose a linear method to generate the sanitized data $Y$ with the same alphabet $\mathcal{Y} = \mathcal{X}$ that attains local differential privacy (LDP) and log-lift at the same time. It is revealed that both LDP and log-lift are inversely proportional to the statistical distance between conditional probability $P_{Y|S}(x|s)$ and marginal probability $P_{Y}(x)$: the closer the two probabilities are, the more private $Y$ is. Specifying $P_{Y|S}(x|s)$ that linearly reduces this distance $|P_{Y|S}(x|s) - P_Y(x)| = (1-\alpha)|P_{X|S}(x|s) - P_X(x)|,\forall s,x$ for some $\alpha \in (0,1]$, we study the problem of how to generate $Y$ from the original data $S$ and $X$. The Markov randomization/sanitization scheme $P_{Y|X}(x|x') = P_{Y|S,X}(x|s,x')$ is obtained by solving linear equations. The optimal non-Markov sanitization, the transition probability $P_{Y|S,X}(x|s,x')$ that depends on $S$, can be determined by maximizing the data utility subject to linear equality constraints. We compute the solution for two linear utility function: the expected distance and total variance distance. It is shown that the non-Markov randomization significantly improves data utility and the marginal probability $P_X(x)$ remains the same after the linear sanitization method: $P_Y(x) = P_X(x), \forall x \in \mathcal{X}$.