摘要
针对连续位置服务查询的隐私问题,提出一种面向位置相关性的差分扰动机制.首先,提出攻击者差分隐私度量模型,量化可用性泄露在时序相关性中导致的隐私风险.其次利用差分隐私中的Laplace扰动构建噪音查询矩阵和基于距离的可用性扰动机制,抵抗基于查询矩阵的数据分析攻击.最后,利用真实数据集实验分析,结果显示本方案提供了更好的隐私保证.
To solve the location privacy problem of continuous queries,author proposes a differential perturbation mechanism for location correlation.Firstly,a model,the attacker differential privacy,is proposed to quantify the privacy caused by usability leakage in temporal correlation.Secondly,noise query matrix and distance-based availability perturbation mechanism are constructed by using Laplace perturbation in differential privacy to resist data analysis attacks based on query matrix.Finally,author further analyzes our scheme on a real dataset.The results illustrate that it offers the meaningful privacy guarantees.
作者
孟玲玉
叶阿勇
MENG Ling-yu;YE A-yong(Fujian Provincial Key Laboratory of Network Security and Cryptology,College of Mathematics and Informatics,Fujian Normal University Fuzhou 350117,China)
出处
《福建师范大学学报（自然科学版）》
CAS
北大核心
2019年第6期21-28,共8页
Journal of Fujian Normal University：Natural Science Edition
基金
国家自然科学基金资助项目(61972096)
福建省自然科学基金资助项目(2018J01780)
关键词
轨迹隐私
差分隐私
时空相关性
位置隐私
trajectory privacy
differential privacy
spatial and temporal correlation
location privacy
