Privacy Preserving Trajectory Data Publishing with Personalized Differential Privacy

Abstract

With the development of location-based applications, more and more trajectory data are collected and applied. Trajectory data often contains user's sensitive information, and direct release may pose a threat to users' privacy. Differential privacy, as a privacy preserving method with solid mathematical foundation, has been widely used in trajectory data publishing. However, current methods based on differential privacy can not fully realize the personalized trajectory privacy protection. In this paper, an optimal personalized trajectory differential privacy mechanism is proposed to balance the privacy protection and data utility. Firstly, we filter out the templet trajectory based on the semantic similarity of trajectories, and propose a privacy level allocation method based on stay-point and frequent sub-trajectory. Then, the privacy levels of all users' locations are obtained according to the location matching results. Combined with the optimal location differential privacy mechanism, we disturb the location points on the user's trajectory before publishing, where different location privacy levels correspond to different privacy budgets. Experiments on real-world datasets show that compared with traditional differential privacy, our mechanism provides a better tradeoff between privacy protection and data utility.