arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.07884cs.DScs.CRcs.CYstat.AP
收藏

纵向数据集合的差分隐私合成数据持续发布

Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections

Mark Bun, Marco Gaboardi, Marcel Neunhoeffer, Wanrong Zhang

AI总结:

针对纵向数据持续发布的隐私问题,提出持续合成数据生成算法,支持固定时间窗口和累积时间查询,误差率近紧,并在美国普查数据上验证性能。

摘要:

受医学和社会科学研究中长期纵向研究中隐私问题的驱动,我们研究了从纵向数据集合中持续发布差分隐私合成数据的问题。我们引入一个模型,在每个时间步中,每个个体报告一个新的数据元素,合成器的目标是以一致的方式增量更新合成数据集,以捕获丰富类别的统计属性。我们给出了持续合成数据生成算法,这些算法保留两种基本类型的查询:固定时间窗口查询和累积时间查询。我们展示了这些算法错误率的近乎紧的上界,并在来自美国人口普查局收入与项目参与调查的规模现实的数据集上证明了它们的实证性能。

英文摘要:

Motivated by privacy concerns in long-term longitudinal studies in medical and social science research, we study the problem of continually releasing differentially private synthetic data from longitudinal data collections. We introduce a model where, in every time step, each individual reports a new data element, and the goal of the synthesizer is to incrementally update a synthetic dataset in a consistent way to capture a rich class of statistical properties. We give continual synthetic data generation algorithms that preserve two basic types of queries: fixed time window queries and cumulative time queries. We show nearly tight upper bounds on the error rates of these algorithms and demonstrate their empirical performance on realistically sized datasets from the U.S. Census Bureau's Survey of Income and Program Participation.

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。

↑