基于用户偏好和位置分布的假位置生成方法  

Dummy Location Generation Method Based on User Preference and Location Distribution

作　　者：王辉[1] 朱国宇 申自浩[1] 刘琨[1] 刘沛骞[1] WANG Hui;ZHU Guo-yu;SHEN Zi-hao;LIU Kun;LIU Pei-qian(College of Computer Science and Technology,Henan Polytechnic University,Jiaozuo,Henan 454003,China)

机构地区：[1]河南理工大学计算机科学与技术学院,河南焦作454003

出　　处：《计算机科学》2021年第7期164-171,共8页Computer Science

基　　金：国家自然科学基金(61300216)。

摘　　要：传统的基于k-匿名机制的假位置生成算法生成的假位置的合理性较低,易被攻击者利用边信息进行攻击。针对此问题,提出了SPDGM算法。首先,定义语义加权有向图,描述语义的时间分布和语义转移关系;其次,为解决仅考虑位置历史概率产生的抵抗能力弱的问题,提出了位置可信度,统一考虑了位置历史概率和大众的评价信息;再次,为避免假位置分布过于密集,定义了离散度,以控制假位置的分布情况;最后,生成语义安全且分布稀疏的匿名集。实验证明,在语义攻击下SPDGM算法具有更低的被识别率,更高的隐私保护强度;在考虑语义攻击的算法中,SPDGM算法的运行时间更短。因此,SPDGM算法具有可行性与实用性。The traditional dummy location generation algorithm based on k-anonymity mechanism has low rationality and is vulnerable to attack by attackers using side information.Aiming at solving this problem,the SPDGM algorithm is proposed.Firstly,this algorithm defines the semantic weighted digraph to describe the time distribution and semantic transfer relationship of semantics.Secondly,for the sake of solving the problem of weak resistance caused by only considering the historical probability of location,this algorithm defines the location credibility,which considers the historical probability of location and the evaluation information of the public.Thirdly,in order to avoid the dense distribution of dummy location,the dispersion degree is defined to control the distribution of dummy location.Finally,this algorithm generates an anonymous set whose semantics safe and distribution sparsely.The experimental results show that the SPDGM algorithm has lower recognition rate and higher privacy protection strength under the semantic attack,and the running time of the algorithm considering semantic attack is lower.Therefore,SPDGM algorithm is feasibility and practicability.

关 键 词：假位置 语义转移 分布度量 用户偏好 位置隐私保护 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]