这项工作展示了如何私下和更准确地估计向量对之间的欧氏距离。输入向量$x$和$y$被映射到差异私有草图$x'$和$y'$,从中可以估计$x$和$y$之间的距离。我们的估计器依赖于Kane \& Nelson的Sparser Johnson-Lindenstrauss构造(Journal of the ACM 2014),对于任何$0<α,β<1/2$,该构造具有最佳输出维度$k=Θ(α^{-2}\log(1/β))$和稀疏度$s=O(α^{-1}\log(1/β))$。我们结合的建设凯恩\和纳尔逊与拉普拉斯或高斯机制从差分隐私文献,根据隐私参数$\varepsilon$和$δ$。我们还建议Ailon \& Chazelle(SIAM Journal of Computing 2009)的快速约翰逊-林登施特劳斯变换(FJLT)的差分私有版本,它为某些参数的方差提供了速度上的权衡。我们回答了Kenthapadi等人提出的一个开放性问题。(Journal of Privacy and Confidential 2013)通过分析欧氏距离估计器的隐私和效用保证,依赖于拉普拉斯而不是高斯噪声。我们证明,拉普拉斯机制产生较低的方差比高斯机制时,$δ<β^{O(1/α)}$。因此,我们的工作比Kenthapadi等人的工作有所改进。通过对足够小的$δ$给出具有较低方差的更有效的估计器。我们的草图还实现了\emph{pure}差分隐私作为拉普拉斯机制的一个整洁的副作用,而不是高斯机制的\emph{approximate}差分隐私保证,这可能对某些设置不够强。
英文摘要:
This work shows how to privately and more accurately estimate Euclidean distance between pairs of vectors. Input vectors $x$ and $y$ are mapped to differentially private sketches $x'$ and $y'$, from which one can estimate the distance between $x$ and $y$. Our estimator relies on the Sparser Johnson-Lindenstrauss constructions by Kane \& Nelson (Journal of the ACM 2014), which for any $0<α,β<1/2$ have optimal output dimension $k=Θ(α^{-2}\log(1/β))$ and sparsity $s=O(α^{-1}\log(1/β))$. We combine the constructions of Kane \& Nelson with either the Laplace or the Gaussian mechanism from the differential privacy literature, depending on the privacy parameters $\varepsilon$ and $δ$. We also suggest a differentially private version of Fast Johnson-Lindenstrauss Transform (FJLT) by Ailon \& Chazelle (SIAM Journal of Computing 2009) which offers a tradeoff in speed for variance for certain parameters. We answer an open question by Kenthapadi et al.~(Journal of Privacy and Confidentiality 2013) by analyzing the privacy and utility guarantees of an estimator for Euclidean distance, relying on Laplacian rather than Gaussian noise. We prove that the Laplace mechanism yields lower variance than the Gaussian mechanism whenever $δ<β^{O(1/α)}$. Thus, our work poses an improvement over the work of Kenthapadi et al.~by giving a more efficient estimator with lower variance for sufficiently small $δ$. Our sketch also achieves \emph{pure} differential privacy as a neat side-effect of the Laplace mechanism rather than the \emph{approximate} differential privacy guarantee of the Gaussian mechanism, which may not be sufficiently strong for some settings.
A Simple Differentially Private Algorithm for Global Minimum Cut
在这篇文章中,我们提出了一个简单的差分私有算法的全球最小割问题,只使用一个调用的指数机制。这个问题首先由Gupta等人研究。[2010],他们给出了一个具有接近最优效用保证的差分私有算法。我们在许多方面改进了他们的工作:我们的算法比Gupta et al. [2010]中给出的算法更简单,更自然,更有效,而且提供了更好的隐私和实用性保证。
Differentially Private Algorithms for Clustering with Stability Assumptions
Ben-Gurion University of the Negev(内盖夫本-古里安大学)
本文研究了在输入稳定性假设下的差分私有聚类问题。尽管关于差分隐私的研究越来越多,特别是关于差异隐私聚类的研究,但只有三项研究(Nissim et al. 2007,Wang et al. 2015,Huang et al. 2018)研究了私下聚类“好”k均值实例的问题,这三个都依赖于样本,聚合框架和所有三个测量实用程序在真正的集群中心和返回的中心之间的Wasserstein距离私有算法在这项工作中,我们改进了这一系列的多轴工作。我们提出了一个简单得多的算法聚类稳定的输入(不依赖于样本和聚合框架),并分析其效用的Wasserstein距离和k-means成本。此外,我们的算法有直接的类似物“好”的k-中位数的实例和本地模型的差分隐私。