跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2602.06756 · v3

f-Differential Privacy Filters: Validity and Approximate Solutions

首次提交 2026-02-06 23:04
版本更新 2026-11-07 20:35
雷达观测 2026-11-10 11:14
arXiv ↗PDF ↗

摘要

Accounting for privacy loss under fully adaptive composition---where mechanism choice and privacy parameters may depend on the history of prior outputs---is a central challenge in differential privacy (DP). Here, privacy filters are stopping rules ensuring a prescribed global budget is not exceeded. A leading candidate for optimal filter design is ff-DP, which characterizes the full extent of adversarial hypothesis testing and recovers (ε,δ)(\varepsilon,δ)-DP through piece-wise linear trade-off functions, while enabling tight (ε,δ)(\varepsilon,δ)-DP accounting in standard compositions via tensor products. Yet whether such filters can be correctly defined under ff-DP remains unclear. We show that the natural ff-DP filter---tracking path-wise accumulating tensor products and stopping when the prescribed curve is crossed---is fundamentally invalid, precluding the direct use of standard efficient numerical Fast-Fourier-Transform accounting in the fully adaptive setting. We characterize this failure, establishing necessary and sufficient conditions for the natural filter's validity. Furthermore, we prove a fully adaptive central limit theorem for ff-DP, establishing Gaussian convergence of cumulative privacy losses under full adaptivity. As a demonstration, we construct a closed-form approximate GDP filter for subsampled Gaussian mechanisms that provably outperforms RDP-based accounting in asymptotic regimes (q≪1q\ll 1 and q≈1q\approx 1) without tracking the full trade-off function, demonstrating that the slack in RDP is not intrinsic to adaptive composition---though CLT-based approximations are known to be optimistic at realistic subsampling rates, a limitation that remains an open challenge.

作者备注:NeurIPS 2026. 54 pages, 12 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-07 20:35 · 最新观测版本

f-Differential Privacy Filters: Validity and Approximate Solutions

Accounting for privacy loss under fully adaptive composition---where mechanism choice and privacy parameters may depend on the history of prior outputs---is a central challenge in differential privacy (DP). Here, privacy filters are stopping rules ensuring a prescribed global budget is not exceeded. A leading candidate for optimal filter design is ff-DP, which characterizes the full extent of adversarial hypothesis testing and recovers (ε,δ)(\varepsilon,δ)-DP through piece-wise linear trade-off functions, while enabling tight (ε,δ)(\varepsilon,δ)-DP accounting in standard compositions via tensor products. Yet whether such filters can be correctly defined under ff-DP remains unclear. We show that the natural ff-DP filter---tracking path-wise accumulating tensor products and stopping when the prescribed curve is crossed---is fundamentally invalid, precluding the direct use of standard efficient numerical Fast-Fourier-Transform accounting in the fully adaptive setting. We characterize this failure, establishing necessary and sufficient conditions for the natural filter's validity. Furthermore, we prove a fully adaptive central limit theorem for ff-DP, establishing Gaussian convergence of cumulative privacy losses under full adaptivity. As a demonstration, we construct a closed-form approximate GDP filter for subsampled Gaussian mechanisms that provably outperforms RDP-based accounting in asymptotic regimes (q≪1q\ll 1 and q≈1q\approx 1) without tracking the full trade-off function, demonstrating that the slack in RDP is not intrinsic to adaptive composition---though CLT-based approximations are known to be optimistic at realistic subsampling rates, a limitation that remains an open challenge.

查看此版本解读 →查看此版本原文 ↗