arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1204.2136cs.DS
收藏

Johnson-Lindenstrauss变换本身保护差分隐私

The Johnson-Lindenstrauss Transform Itself Preserves Differential Privacy

Jeremiah Blocki, Avrim Blum, Anupam Datta, Or Sheffet

摘要:

本文证明了一个“老狗”,即--经典的约翰逊-林登施特劳斯变换,“表演新把戏”--它提供了一种新的方式来保护差分隐私。我们表明,如果我们采取两个数据库,$D$和$D'$,使得(i)$D'-D$是一个秩-1矩阵的有界范数和(ii)所有的奇异值的$D$和$D'$是足够大的,然后乘以$D$或$D'$与iid正常高斯向量产生两个统计上接近的分布在差分隐私的意义。此外,输入的小的、确定性的和\emph{public}的改变足以断言$D$的所有奇异值是大的。我们应用约翰逊-林登施特劳斯变换的任务,近似切割查询:在一个图中的边缘交叉$(S,\bar S)$ -削减的数量。我们表明,JL变换允许我们\emph{publish a sanitized graph},保留边缘差分隐私(其中两个图是邻居,如果他们在一个单一的边缘不同),同时只添加$O(|S|/ε)$随机噪声到任何给定的查询(w.h.p)。比较我们的算法的加性噪声,以不同的私人方式回答切割查询的现有算法,我们优于所有其他的小切($|S| = o(n)$)。我们还将我们的技术应用于估计给定矩阵在任何给定方向上的方差的任务。JL变换允许我们\emph{publish a sanitized covariance matrix},其保留关于有界变化的差分隐私(矩阵中的每一行最多可以改变一个范数-1向量),同时添加幅度与矩阵的大小(w.h.p)无关的随机噪声。相比之下,现有的算法引入了一个错误,这取决于矩阵的维数。

英文摘要:

This paper proves that an "old dog", namely -- the classical Johnson-Lindenstrauss transform, "performs new tricks" -- it gives a novel way of preserving differential privacy. We show that if we take two databases, $D$ and $D'$, such that (i) $D'-D$ is a rank-1 matrix of bounded norm and (ii) all singular values of $D$ and $D'$ are sufficiently large, then multiplying either $D$ or $D'$ with a vector of iid normal Gaussians yields two statistically close distributions in the sense of differential privacy. Furthermore, a small, deterministic and \emph{public} alteration of the input is enough to assert that all singular values of $D$ are large. We apply the Johnson-Lindenstrauss transform to the task of approximating cut-queries: the number of edges crossing a $(S,\bar S)$-cut in a graph. We show that the JL transform allows us to \emph{publish a sanitized graph} that preserves edge differential privacy (where two graphs are neighbors if they differ on a single edge) while adding only $O(|S|/ε)$ random noise to any given query (w.h.p). Comparing the additive noise of our algorithm to existing algorithms for answering cut-queries in a differentially private manner, we outperform all others on small cuts ($|S| = o(n)$). We also apply our technique to the task of estimating the variance of a given matrix in any given direction. The JL transform allows us to \emph{publish a sanitized covariance matrix} that preserves differential privacy w.r.t bounded changes (each row in the matrix can change by at most a norm-1 vector) while adding random noise of magnitude independent of the size of the matrix (w.h.p). In contrast, existing algorithms introduce an error which depends on the matrix dimensions.

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。

↑