A Distributed Approach for Privacy Preservation in the Publication of Trajectory Data
Felipe T. Brito, Antonio Cavalcante Araujo Neto, Camila F. Costa, André L. C. Mendonça, Javam C. Machado · 2015
Advancements in mobile computing techniques along with the pervasiveness of location-based services have generated a great amount of trajectory data. These data can be used for various data analysis purposes such as traffic flow analysis, infrastructure planning and understanding of human behavior. However, publishing this amount of trajectory data may lead to serious risks of privacy breach. Quasi-identifiers are trajectory points that can be linked to external information and be used to identify individuals associated with trajectories. Therefore, by analyzing quasi-identifiers, one may be able to trace anonymous trajectories back to individuals with the aid of location-aware social networking applications, for example. Most existing trajectory data anonymization approaches were proposed for centralized computing environments, so they usually present poor performance to anonymize large trajectory data sets. In this paper we propose a distributed and efficient strategy that adopts the km-anonymity privacy model and uses the scalable MapReduce paradigm, which allows finding quasi-identifiers in larger amount of data. We also present a technique to minimize the loss of information by selecting key locations from the quasi-identifiers to be suppressed. Experimental evaluation results demonstrate that our proposed approach for trajectory data anonymization is more scalable and efficient than existing works.