Soft Voting for Policy-Aware Private Data Synthesis

2026-10-08

AI Summary

This study addresses the high sensitivity of hard voting and the failure of policy graph denoising under Blowfish privacy by proposing the BF-Soft framework. Specifically, it introduces a temperature-smoothed soft voting mechanism that decouples sensitivity from the number of candidates. Furthermore, it establishes a closed-form sensitivity bound based on the reachable range of the policy graph to predict smoothing gains and avoid futile computations, while integrating an evolutionary neighbor synthesizer to optimize private data synthesis. Experimental results demonstrate that the proposed method significantly reduces error under strong privacy budgets, reveals an advantage reversal phenomenon under weak budgets, and provides a predictive solution leveraging public data.

Abstract

Blowfish privacy relaxes differential privacy (DP) by protecting only the attribute-value substitutions a data owner specifies as edges of a policy graph. A sparser policy can reduce the noise required by a mechanism, but only when the released statistic changes less across protected substitutions than across arbitrary DP neighbors. We study this question for evolutionary, nearest-neighbor DP synthesizers such as Private Evolution (PE) and its tabular instantiation Tab-PE, which score private records against a candidate population and release a noisy vote histogram. Their hard vote is constant inside each candidate's decision region and jumps at its boundary. Its policy-specific sensitivity therefore equals the full worst-case value whenever at least one protected substitution crosses a boundary, regardless of how short that substitution is. Because every round we examined contained such a substitution, the policy graph gave no reduction in noise. We propose BF-Soft, a temperature-smoothed soft vote whose response changes gradually with distance. Its sensitivity has a tight closed-form bound in the policy graph's reach and the temperature, independent of the number of candidates, and the bound can be computed once before synthesis. It also predicts from the policy alone when policy-aware smoothing cannot substantially reduce noise: protecting a flat categorical or binary attribute drives the reach to its maximum. On real and synthetic datasets under narrow numeric policies, BF-Soft reduces error relative to hard voting at strong privacy budgets, while the advantage reverses at weaker budgets. A public-data pilot predicts when soft voting is beneficial without spending private budget.

Problem

• Blowfish privacy
• differential privacy
• private data synthesis
• hard voting sensitivity
• policy graph

Innovation

• Blowfish privacy
• soft voting
• differential privacy
• policy graph
• data synthesis