arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15815cs.CRcs.DS
收藏

隐私过滤器由余数捕获:自由自然过滤器的特征以及适应性的成本

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity

University of Waterloo(滑铁卢大学);University of British Columbia(不列颠哥伦比亚大学);Google Research(谷歌研究);Google(谷歌);Columbia University(哥伦比亚大学)

Matthew Regehr, Bingshan Hu, Ethan Leeman, Pasin Manurangsi, Pierre Tholoniat, Mathias Lécuyer

AI总结:

本文研究了隐私过滤器,提出余数过滤器统一现有方法,并展示自然过滤器通过精确隐私会计提升效用,同时揭示自然隐私过滤器非免费,且在特定条件下可实现免费。

摘要:

我们研究了隐私过滤器,它们使能够为具有适应性选择隐私特性的差分隐私(DP)机制进行隐私会计。我们开发了一种通用理论,该理论刻画了涉及分析师的交互的最坏隐私损失,其中分析师受某些限制,限制了他们可以提出的查询。我们将这一理论应用于开发余数过滤器,它统一了现有的隐私过滤器。我们开发了高斯DP(GDP)余数过滤器,它严格优于朴素GDP过滤器。我们还展示余数过滤器捕捉了自然过滤器,该过滤器通过利用精确的隐私会计技术提供更高的效用。早期的隐私过滤器仅考虑简单的隐私参数,如Rényi-DP或GDP参数。自然过滤器考虑了每个查询的整个隐私配置文件,承诺更高效地使用给定的隐私预算。我们证明,与其它DP形式不同,自然隐私过滤器通常不免费。我们提出了一种特征,说明当私有查询族在组合时完全有序时,对于给定的预算,允许免费的自然隐私过滤器。特别是,只有当隐私机制族在组合时完全有序时,才允许针对任意隐私预算的免费自然隐私过滤器。最后,我们展示,尽管自然近似DP过滤器在存在适应性对手时可能失效,但其失效程度有限:输出仍保持近似DP,参数至多比预期隐私参数差多项式对数级别。

英文摘要:

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We show that the worst-case privacy loss of interacting with any privacy filter is characterized by a Bellman equation. We apply this theory to develop residue filters, which unify existing privacy filters. We develop the Gaussian DP (GDP) residue filter, which strictly improves upon the naïve GDP filter. We show that, in the average case, this new filter asymptotically permits as many pure DP queries as in the non-adaptive case and a factor $π/2$ more pure DP queries than the naïve GDP filter. We also show that residue filters capture the natural filter, which promises greater utility by leveraging exact privacy accounting techniques. Earlier privacy filters consider only simple privacy parameters such as Rényi-DP or GDP parameters. Natural filters account for the entire privacy profile of every query, promising more efficient use of a given privacy budget. We show that, contrary to other forms of DP, natural privacy filters are not free in general. We present a characterization of when a family of private queries admits free natural filters for a given budget. In particular, only families of privacy mechanisms that are totally-ordered when composed admit free natural privacy filters with respect to an arbitrary privacy budget. Finally, we show that, while the natural approximate-DP filter can fail in the presence of an adaptive adversary, it cannot fail too badly: the output remains approximate-DP with parameters at most poly-logarithmically worse than the intended privacy parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑