arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05707cs.CRcs.DScs.LG
收藏

有界空间下的差分隐私与自适应数据分析

On Differential Privacy and Adaptive Data Analysis with Bounded Space

Ben-Gurion University(本-古里安大学);Tel Aviv University(特拉维夫大学);Google Research(谷歌研究院);Carnegie Mellon University(卡内基梅隆大学);UC Berkeley(加州大学伯克利分校);Rice University(莱斯大学)

Itai Dinur, Uri Stemmer, David P. Woodruff, Samson Zhou

摘要:

我们研究了差分隐私和自适应数据分析这两个相关领域的空间复杂度。具体而言,(1)在标准密码学假设下,我们证明了存在一个问题P,与没有隐私所需的空间相比,该问题P需要以指数方式更多的空间来有效地解决差分隐私。据我们所知,这是私有算法和非私有算法的空间复杂度之间的第一次分离。(2)自适应数据分析的工作重点是理解回答一系列自适应查询所需的样本数量。我们重新审视以前的下限在基础水平,并表明,它们是一个空间瓶颈,而不是采样瓶颈的后果。为了获得我们的结果,我们定义并构建了一个具有多个密钥的加密方案,该加密方案以一种非常特殊的方式承受有限数量的密钥泄漏。

英文摘要:

We study the space complexity of the two related fields of differential privacy and adaptive data analysis. Specifically, (1) Under standard cryptographic assumptions, we show that there exists a problem P that requires exponentially more space to be solved efficiently with differential privacy, compared to the space needed without privacy. To the best of our knowledge, this is the first separation between the space complexity of private and non-private algorithms. (2) The line of work on adaptive data analysis focuses on understanding the number of samples needed for answering a sequence of adaptive queries. We revisit previous lower bounds at a foundational level, and show that they are a consequence of a space bottleneck rather than a sampling bottleneck. To obtain our results, we define and construct an encryption scheme with multiple keys that is built to withstand a limited amount of key leakage in a very particular way.

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。

↑