A Differential Private Mechanism to Protect Trajectory Privacy in Mobile Crowd-Sensing

Abstract

With the fast development of smart mobile devices, the mobile crowd-sensing (MCS) has been witnessed as a new data collection paradigm. In this paper, we consider a scenario that an MCS server tries to collect trajectories from participants. In order to protect the participants location privacy from their own side, we let participants submit noisy data to the server. In addition, we assume that the data collection is delay tolerant which means each participant is allowed to submit his trajectory in a bundle instead of submitting locations one by one. Based on this assumption, we regard each trajectory as a vector in the high dimension space and design a trajectory protection algorithm to perturb the true trajectory before submission. We use the differential privacy (DP) as the privacy model so we can estimate the amount of noise given a privacy level. To evaluate our mechanism, we use real world traffic data collected from Shanghai taxis and compare it with existing work. The results show that our mechanism not only guarantees privacy protection, but also preserves trajectories utility.