arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1711.04740cs.DS
收藏

重量级人物与局部隐私的结构

Heavy Hitters and the Structure of Local Privacy

Mark Bun, Jelani Nelson, Uri Stemmer

摘要:

我们提出了一个新的局部差分隐私算法的重打击者问题,实现最佳的最坏情况下的错误作为所有标准考虑参数的函数。先前的工作得到的出错率最佳地取决于用户的数量,域的大小,和隐私参数,但次最佳地取决于故障概率。我们加强现有的下限的错误,将失败的概率,并表明我们的新的上限是紧相对于这个参数。我们的下界是基于对局部私有协议结构的新理解。我们进一步发展这些想法,得到以下的一般结果超出了重打击。$\bullet$高级分组:在局部模型中,$k$用户的组隐私与$\approx \sqrt{k}$成比例地降级,而不是像在中心模型中那样在$k$中线性地降级。更强的群体隐私产生更好的最大信息保证,以及更强的下限(通过“包装参数”),超过中心模型。$\bullet$基于Basily和Smith(STOC 2015)的转换,我们给出了从任何非交互式近似私有本地协议到纯私有本地协议的通用转换。再次与中心模型相比,这表明我们不能通过从纯局部隐私移动到近似局部隐私来获得更准确的算法。

英文摘要:

We present a new locally differentially private algorithm for the heavy hitters problem which achieves optimal worst-case error as a function of all standardly considered parameters. Prior work obtained error rates which depend optimally on the number of users, the size of the domain, and the privacy parameter, but depend sub-optimally on the failure probability. We strengthen existing lower bounds on the error to incorporate the failure probability, and show that our new upper bound is tight with respect to this parameter as well. Our lower bound is based on a new understanding of the structure of locally private protocols. We further develop these ideas to obtain the following general results beyond heavy hitters. $\bullet$ Advanced Grouposition: In the local model, group privacy for $k$ users degrades proportionally to $\approx \sqrt{k}$, instead of linearly in $k$ as in the central model. Stronger group privacy yields improved max-information guarantees, as well as stronger lower bounds (via "packing arguments"), over the central model. $\bullet$ Building on a transformation of Bassily and Smith (STOC 2015), we give a generic transformation from any non-interactive approximate-private local protocol into a pure-private local protocol. Again in contrast with the central model, this shows that we cannot obtain more accurate algorithms by moving from pure to approximate local privacy.

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。

↑