SLAT: Sub-Trajectory Linkage Attack Tolerance Framework for Privacy-Preserving Trajectory Publishing
Xiangwen Liu, Liangmin Wang, Yuquan Zhu · 2018
The pervasiveness of location-aware devices offers terrific opportunities for analyzing and mining human mobility. Yet, sharing of trajectory data poses personal privacy issues. Consider a dataset of trajectories, containing detailed movement information about individuals, published with sensitive attributes such as disease, income, etc. One can use partial trajectory knowledge, comprised of non-sensitive location information, for identity, sensitive locations and sensitive values of target individuals. We present SLAT, a Sub-trajectory Linkage Attack Tolerance framework based on anonymization techniques of trajectory splitting, location suppression and sensitive value generalization, to prevent privacy disclosure while preserving accurate trajectory data for query and mining. Experiments show that SLAT is effective to improve data utility of anonymized trajactory data when compared with previous work.