arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.05926cs.ITcs.CRmath.IT
收藏

稳健隐私保证的效用成本

The Utility Cost of Robust Privacy Guarantees

Hao Wang, Mario Diaz, Flavio P. Calmon, Lalitha Sankar

摘要:

考虑一个具有公共和私有特征的数据集的数据发布设置。发布者的目标是最大化公开数据集中关于公共特征的信息量,同时保持泄露的关于私有特征的信息有界。本文的目标是分析隐私机制的性能,构建匹配的分布从数据集学习。考虑两种不同的情况:(i)机制被设计为提供一个隐私保证的学习分布;和(ii)机制被设计为提供一个隐私保证的学习分布的给定邻域中的每个分布。对于第一种情况,给定任何隐私机制,上界的学习和真实分布的隐私效用保证之间的差异。在第二种情况下,上界的效用减少所产生的提供一个统一的隐私保证。

英文摘要:

Consider a data publishing setting for a data set with public and private features. The objective of the publisher is to maximize the amount of information about the public features in a revealed data set, while keeping the information leaked about the private features bounded. The goal of this paper is to analyze the performance of privacy mechanisms that are constructed to match the distribution learned from the data set. Two distinct scenarios are considered: (i) mechanisms are designed to provide a privacy guarantee for the learned distribution; and (ii) mechanisms are designed to provide a privacy guarantee for every distribution in a given neighborhood of the learned distribution. For the first scenario, given any privacy mechanism, upper bounds on the difference between the privacy-utility guarantees for the learned and true distributions are presented. In the second scenario, upper bounds on the reduction in utility incurred by providing a uniform privacy guarantee are developed.

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。

↑