基于轨迹特征及动态邻近性的轨迹匿名方法研究

Research on Trajectory Privacy Preserving Method Based on Trajectory Characteristics and Dynamic Proximity

移动社会网络的兴起以及移动智能终端的发展产生了大量的时空轨迹数据,发布并分析这样的时空数据有助于改善智能交通,研究商圈的动态变化等.然而,如果攻击者能够识别出轨迹对应的用户身份,将会严重威胁到用户的隐私信息.现有的轨迹匿名算法在度量相似性时仅考虑轨迹在采样点位置的邻近性,忽略轨迹位置的动态邻近性,因此产生的匿名轨迹集合可用性相对较低.针对这一问题,本文提出了邻域扭曲密度和邻域相似性的概念,充分考虑轨迹位置的动态邻近性,并分别提出了基于邻域相似性和邻域扭曲密度的轨迹匿名算法;前者仅考虑了轨迹位置的动态邻近性,后者不仅能衡量轨迹位置的动态邻近性,而且在聚类过程中通过最小化邻域扭曲密度来减少匿名集合的信息损失.最后,在合成轨迹数据集和真实轨迹数据集上的实验结果表明,本文提出的算法具有更高的数据可用性.

The rise of mobile social networks as well as mobile intelligent terminal has generated a lot of spatial-temporal trajectory data, publishing and analyzing such data is essential to improve transportation, to understand the dynamics of the economy in a region, etc. However, it will be a serious threat to the user＇s privacy, if adversary is able to identify user＇s identity corresponding to the trajectory. While calculating similarity of trajectories, the existing methods consider only locations proximity of the sampling point in the trajectory, and ignore the dynamic proximity of locations in the trajectory. So the produced trajectory anonymity set has a low utility. To solve this problem, we first present the concept of neighborhood similarity and neighborhood distortion density to fully consider the dynamics proximity of locations in the trajectory, and then propose two algorithms, i.e., trajectory anonymity algorithm based on neighborhood similarity and trajectory anonymity algorithm based on trajectory neighborhood distortion density. The former one only considers the dynamics proximity of locations in the trajectory, while the latter one also reduces information loss of anonymous collection by minimizing neighborhood distortion density during the clustering process. Finally, experimental results on a synthetic data set and a real-life data set demonstrate that our method offers better utility than comparable previous proposals in the literature.