差分隐私保护下的数据分级发布机制

A differentially-private mechanism for multi-level data publishing

隐私保护技术解决了数据发布过程中的隐私泄露问题,然而当前的数据发布技术大多只面向查询用户发布同一隐私保护级别的数据,并未考虑查询用户等级不同的情况。在所提出的满足差分隐私的数据分级发布机制中,数据发布方利用隐私预算参数不同的拉普拉斯机制对数据查询结果进行隐私保护处理,实现了输出隐私保护程度不同的查询结果。在依据付费或权限对查询用户分级后,数据发布方为等级较高(低)的查询用户发布隐私保护程度较低(高)的查询结果,使得查询用户可使用错误率较低(高)的数据,达到了隐私数据分级发布的效果。实验结果与安全性分析表明该机制在抵抗背景知识攻击的同时还可有效地实现输出错误率不同的分级查询结果。

Privacy preserving technology had addressed the problem of privacy leakage during data publishing process, however, current data publishing technologies mostly focused on publishing privacy preserving data with single level, without considering some scenarios of multi-level users. Therefore, a differentially-private mechanism for multi-level data publishing was proposed. The proposed mechanism employed the Laplace mechanism with different privacy budgets to output results with different privacy protection levels. After the user＇s level was determined according to the charge or privilege of that specific user, the goal that a user with high（low） level can only use the output result with low（high） privacy protection level which had low（high） error rate could be achieved. Finally, the evaluation results and security analysis show that our proposed framework can not only prevent from background knowledge attack, but also achieve multi-level data publishing with different error rates effectively.