Tracking Moving Objects in Anonymized Trajectories

A-PIE: An algorithm for preserving privacy, quality of information, and energy consumption in Participatory Sensing Systems

“…One application of PS systems is to support the urban and transportation planning process inferring the most popular travel routes in a city and understanding the human travel behavior [39,40,41]. Therefore, PS systems have generated significant interest in the collection of spatio-temporal data for moving objects [42,43]. However, the availability of such data at a centralized location raises concerns regarding the privacy of mobile device clients since an adversary could use a trajectory-estimation method over such data in order to compromise the users' privacy [21,44,45].…”

“…Recall that the adversary has access to privacy-protected data, then he may have access to modified or non-modified data based on the privacy-preserving mechanism applied in the system. In the case of a PS system using an non-attribute-modification mechanism, the adversary has access to the actual location, and he might use a traditional tracking algorithm in order to reconstruct the participant's trajectory [42]. In the case of an attribute-modification mechanism, the adversary does not have access to actual but a modified location, therefore, he needs to estimate the location where each record was generated as well as the records that belongs to the same trajectory.…”

“…Therefore, the adversary aims to reconstruct the trajectory followed by the participant. In general, the trajectory estimation problem is to find a set of N trajectories given a history H spanning P timestamps of exactly N objects [42]. Each trajectory T k is defined as follows:…”