Anonymization of Trajectory Data

Trajectories of mobile objects, are automatically collected in huge quantities. Publishing and exploiting such data is essential to improve planning, but it threatens the privacy of individuals: re-identification of the individual behind a trajectory is easy unless precautions are taken. We present two heuristics for privacy-preserving publication of trajectories. Both of them publish only true locations. The first heuristic is based on trajectory microaggregation and on location permutation; it effectively achieves trajectory k-anonymity. The second heuristic is based only on location permutation; it gives up trajectory k-anonymity and aims at a different property named location k-diversity. The advantage of the second heuristic is that it takes into account reachability constraints when computing anonymized trajectories.