arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05453cs.LGcs.DSstat.ML
收藏

一种新的Oracle高效的私有合成数据发布算法

New Oracle-Efficient Algorithms for Private Synthetic Data Release

University of Minnesota(明尼苏达大学);Harvard University(哈佛大学);Boston University(波士顿大学);IBM Research(IBM研究院)

Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Zhiwei Steven Wu

摘要:

我们提出了三种新的算法,用于构建差异私人合成数据--一个消毒版本的敏感数据集,大约保留了大量的统计查询的答案。所有这三种算法都是\emph{oracle-efficient},因为它们在访问优化预言时是计算高效的。这样的预言可以使用许多现有的(非私有的)优化工具来实现,例如复杂的整数规划求解器。虽然合成数据的准确性取决于预言机的优化性能,但即使在最坏的情况下,算法也能满足差分隐私。对于所有这三种算法,我们都为准确性和隐私性提供了理论保证。通过实证评估,我们表明,我们的方法规模以及与数据的维数和查询的数量。与最先进的高维矩阵机制\cite{McKennaMHM18}相比,我们的算法在大工作量和高隐私机制(对应于低隐私损失$\varepsilon$)下提供了更好的准确性。

英文摘要:

We present three new algorithms for constructing differentially private synthetic data---a sanitized version of a sensitive dataset that approximately preserves the answers to a large collection of statistical queries. All three algorithms are \emph{oracle-efficient} in the sense that they are computationally efficient when given access to an optimization oracle. Such an oracle can be implemented using many existing (non-private) optimization tools such as sophisticated integer program solvers. While the accuracy of the synthetic data is contingent on the oracle's optimization performance, the algorithms satisfy differential privacy even in the worst case. For all three algorithms, we provide theoretical guarantees for both accuracy and privacy. Through empirical evaluation, we demonstrate that our methods scale well with both the dimensionality of the data and the number of queries. Compared to the state-of-the-art method High-Dimensional Matrix Mechanism \cite{McKennaMHM18}, our algorithms provide better accuracy in the large workload and high privacy regime (corresponding to low privacy loss $\varepsilon$).

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。

↑