基于差分隐私机制的位置数据隐私保护策略

Location data privacy protection based on differential privacy mechanism

位置定位服务技术作为一种全新的移动计算服务,在日常生活中应用广泛。一方面,数据信息共享极大地方便了人们的日常生活,另一方面也存在由于泄露个人敏感信息而产生的弊端,因此如何保护好位置数据是关键。由于位置数据具有价值高和低密度的特性,导致现有的隐私保护方法很难兼顾数据的保护和数据的效用性。基于差分隐私机制的位置数据隐私保护策略通过采用多级查询树的结构来查询和发布保护后的数据,并保持了数据项间的联系。首先构建多级查询树(位置搜索树),然后遍历查询树,使用差分隐私的指数机制来选取访问频率高的k项,最后通过拉普拉斯机制给选取的k项进行加噪。实验表明,相比于其他保护策略,基于差分隐私机制的位置数据隐私保护策略可用性和数据保护程度高,算法运行时间少,效率更高。

Now many applications of location data have facilitated people’s daily life,so location data service is called a kind of new mobile computing service.However,publishing location data may divulge individual sensitive information and then affect people’s normal life.On the other hand,if they cannot mine and share data information,data will lose its value for serving people’s society.So,it is double-edged sword that how to use location data.Currently many existing privacy protection schemes can not provide the balance of utility and protection for data.Furthermore,as location data is discrete,some existing privacy protection schemes are difficult to protect location data in data mining.This paper proposed that a location data privacy protection scheme was based on differential privacy mechanism,which employed the structure of multilevel query tree to query and publish location data result on database.In the proposed scheme,they first constructed the structure of multi-level query tree on database,and then made double processes of selecting data on accessing frequencies by the exponential mechanism and one process of adding noises to accessing frequencies by the Laplace’s mechanism on the multi-level query tree.Compared with other schemes,what the experiments show is the data’s availability and privacy protection level of the proposed scheme is more higher,and the running time of the proposed algorithms is less.