Between Close Enough to Reveal and Far Enough to Protect: a New Privacy Region for Correlated Data

TL;DR

This paper introduces a new privacy region for correlated data, balancing privacy and utility, by analyzing data-independent mechanisms and proposing a data-dependent approach that leverages correlation information.

Contribution

It characterizes the limitations of data-independent mechanisms and proposes a novel data-dependent redaction mechanism to improve utility in correlated data scenarios.

Findings

Data-independent mechanisms have upper bounds on utility with correlated data.

The proposed data-dependent mechanism outperforms data-independent methods.

The approach effectively balances privacy and utility in Markov-modeled data.

Abstract

When users make personal privacy choices, correlation between their data can cause inadvertent leakage about users who do not want to share their data by other users sharing their data. As a solution, we consider local redaction mechanisms. As prior works proposed data-independent privatization mechanisms, we study the family of data-independent local redaction mechanisms and upper-bound their utility when data correlation is modeled by a stationary Markov process. In contrast, we derive a novel data-dependent mechanism, which improves the utility by leveraging a data-dependent leakage measure.