arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.00010cs.DScs.CRstat.ML
收藏

用于差分隐私的离散高斯分布

The Discrete Gaussian for Differential Privacy

Clément L. Canonne, Gautam Kamath, Thomas Steinke

AI总结:

本文提出在差分隐私中使用离散高斯分布替代连续高斯噪声,以解决有限计算机表示误差导致的隐私破坏和离散数据可解释性下降问题,并从理论和实验上证明其提供与连续高斯噪声基本相同的隐私和精度保证,同时给出高效的精确采样算法。

摘要:

构建差分隐私系统的一个关键工具是在敏感数据集上评估的函数输出中添加高斯噪声。然而,使用连续分布会带来一些实际挑战。首先,有限计算机无法精确表示来自连续分布的样本,且已有工作表明看似无害的数值误差可能完全破坏隐私。此外,当底层数据本身是离散的(如人口计数)时,添加连续噪声会降低结果的可解释性。鉴于这些不足,我们在差分隐私背景下引入并分析了离散高斯分布。具体而言,我们从理论和实验上证明,添加离散高斯噪声可提供与添加连续高斯噪声基本相同的隐私和精度保证。我们还提出了一种简单高效的算法,可从该分布中进行精确采样。这证明了其在隐私保护下回答计数查询,或更一般地,低敏感度整数查询中的适用性。

英文摘要:

A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and foremost, finite computers cannot exactly represent samples from continuous distributions, and previous work has demonstrated that seemingly innocuous numerical errors can entirely destroy privacy. Moreover, when the underlying data is itself discrete (e.g., population counts), adding continuous noise makes the result less interpretable. With these shortcomings in mind, we introduce and analyze the discrete Gaussian in the context of differential privacy. Specifically, we theoretically and experimentally show that adding discrete Gaussian noise provides essentially the same privacy and accuracy guarantees as the addition of continuous Gaussian noise. We also present an simple and efficient algorithm for exact sampling from this distribution. This demonstrates its applicability for privately answering counting queries, or more generally, low-sensitivity integer-valued queries.

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。

↑