Differential privacy protection method based on published trajectory cross-correlation constraint

Abstract

Aiming to solve the problem of low data utilization and privacy protection, a personalized differential privacy protection method based on cross-correlation constraints is proposed. By protecting sensitive location points on the trajectory and their affiliated sensitive points, this method combines the sensitivity of the user's trajectory location and user privacy protection requirements and privacy budget to propose a (R,∈) -extended differential privacy protection model. Using autocorrelation Laplace transform, specific Gaussian white noise is transformed into noise that is related to the user's real trajectory sequence in both time and space. Then the noise is added to the user trajectory sequence to ensure spatio-temporal correlation between the noise sequence and the user trajectory sequence. This defines the cross-correlation constraint mechanism of the published trajectory sequence. By superimposing the real trajectory sequence on the user's noise sequence that satisfies the autocorrelation, a published trajectory sequence that satisfies the cross-correlation constraint condition is established to provide strong privacy guarantees against adversaries. Finally, the feasibility, effectiveness and rationality of the algorithm are verified by simulation experiments, and the proposed method is compared with recent studies in the same field on basis of merits and weakness and so on.