Personalized semantic trajectory privacy preservation through trajectory reconstruction

Trajectory data gathered by mobile positioning techniques and location-aware devices contain plenty of sensitive spatial-temporal and semantic information, and can support many applications through data analysing and mining. However, attribute-linkage and re-identification attacks on such data may cause privacy leakage, and lead to unexpected serious consequences. Existing privacy preserving techniques for trajectory data often ignore the different privacy requirements of different moving objects or largely scarify the availability of trajectory data. In view of these issues, we propose an effective personalized trajectory privacy preserving method which can strike a good balance between user-defined privacy requirement and data availability in off-line trajectory publishing scenario. The main idea is to firstly label semantic attributes of all sampling points on the trajectory and build a corresponding taxonomy tree, next extract sensitive stop points, then for different types of sensitive stop points, adopt different strategies to select the appropriate points of user interests to replace while considering user speed and avoiding reverse mutation, and finally publish the reconstructed trajectory. Besides, to make our method more realistic we further consider possible obstacles appeared in the user space environment. In the experiments, average identification possibility, trajectory semantic consistency and trajectory shape similarity are taken as evaluation criteria, and the performance of our method is comprehensively evaluated. The results show that our method can improve the user trajectory availability as much as possible, while effectively achieving the different trajectory privacy requirements.