Differentially Private Consistent Release of Counting Queries

2026-07-12

AI Summary

This work addresses the problem of minimizing the worst-case error probability in releasing count queries under both (ε,δ)-differential privacy and query consistency constraints. By integrating techniques from differential privacy, information theory, and convex optimization, the authors derive, for the first time, a closed-form optimal mechanism and fully characterize the structural properties of all optimal mechanisms. The framework is further extended to scenarios involving a fixed stochastic channel cascaded after the privacy mechanism, and necessary and sufficient conditions are established under which no performance loss occurs due to the channel. Notably, in the high-privacy regime, uncoded transmission using M-ary phase-shift keying (PSK) over an additive white Gaussian noise channel is shown to be near-optimal, with rigorous upper and lower bounds on its performance provided.

Abstract

We study the problem of releasing counting-query outputs through a stochastic mechanism that is both consistent and \((ε,δ)\)-differentially private. Consistency requires the released value to lie within the feasible range of the query, while utility is measured by the worst-case probability of error. We first derive a closed-form expression for the minimum achievable error probability and obtain an explicit optimal mechanism. By exploiting the active differential privacy constraints satisfied by this mechanism, we then characterize the entire class of optimal mechanisms via a propagation argument, identifying the structural properties shared by all optimizers. We next extend the framework to the setting in which the privacy mechanism is cascaded with an arbitrary fixed stochastic transformation representing a predetermined portion of the communication medium between the source and the destination. We first establish necessary and sufficient conditions under which this partial fixation of the medium incurs no loss in utility. We then derive upper and lower bounds on the optimal achievable performance based on convex mixing and spectral perturbation. Finally, we apply the theory to (M)-ary phase-shift keying (PSK) transmission over an additive white Gaussian noise (AWGN) channel and show that uncoded transmission is effectively optimal in the high-privacy regime.

Problem

• differential privacy
• counting queries
• consistency
• utility
• stochastic mechanism

Innovation

• differential privacy
• counting queries
• optimal mechanism
• consistency
• stochastic transformation