Multi-tier Differential Private Query Release

2026-06-13

AI Summary

This work addresses the challenge of answering identical queries under heterogeneous privacy budgets in multi-analyst settings, where varying trust levels or willingness to pay necessitate differentiated privacy guarantees. Existing approaches struggle to simultaneously control cumulative privacy loss and preserve query utility. The paper proposes the first unified framework that strictly bounds cumulative privacy loss within a global budget while nearly achieving the optimal utility of single-level mechanisms. The framework is both general and mechanism-specific: it leverages characteristic functions of noise distributions to derive a generic solution for centralized models—such as the two-sided geometric mechanism—and introduces a budget transformation primitive along with a templated strategy tailored to the Subset mechanism under local differential privacy. Empirical evaluations demonstrate that the approach effectively constrains privacy loss and significantly enhances utility across diverse mechanisms and budget allocations.

Abstract

Answering statistical queries over sensitive data under differential privacy (DP) is a common task in many settings, including databases, mobile computing, and data markets. In these scenarios, multiple analysts may issue the same query, while receiving answers generated under different privacy budgets due to differences in trust levels or willingness to pay. Existing approaches for such multi-tier DP queries either incur excessive cumulative privacy loss or suffer from suboptimal utility. In this paper, we propose a framework for multi-tier DP query release that simultaneously bound the cumulative privacy loss by the maximum privacy budget among all queries and achieve optimal utility comparable to that of single-tier mechanisms. Our framework applies to different classes of DP mechanisms. For noise-adding mechanisms (e.g., count queries with the two-sided Geometric mechanism in the curator model), we develop a general solution based on the characteristic functions of noise distributions. For other mechanisms (e.g., count queries under the local DP model with the Subset mechanism), we design mechanism-specific primitives for budget transformation and introduce a template-based strategy that attains optimal utility across different privacy regimes. Experimental results demonstrate the effectiveness of our framework.

Problem

• differential privacy
• multi-tier queries
• privacy budget
• statistical query
• utility

Innovation

• multi-tier differential privacy
• privacy budget
• optimal utility
• noise distribution
• local differential privacy