赢得NIST竞赛:一种可扩展的通用方法来区分私有合成数据
Winning the NIST Contest: A scalable and general approach to differentially private synthetic data
摘要:
我们提出了一种通用的方法,用于差分私人合成数据生成,包括三个步骤:(1)选择一个低维边缘的集合,(2)测量这些边缘与噪声添加机制,(3)生成合成数据,保留测量的边缘很好。这种方法的核心是Private-PGM,这是一种后处理方法,用于从其边缘的噪声测量中估计高维数据分布。我们提出了两种机制,NIST-MST和MST,这是这种一般方法的实例。NIST-MST是2018年NIST差分隐私合成数据竞赛的获胜机制,MST是一种新机制,可以在更一般的设置中工作,同时仍然执行NIST-MST的性能。我们相信,我们的一般方法应该是广泛的利益,并可以在未来的机制,合成数据的生成。
英文摘要:
We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.
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。