Personalized Privacy-Preserving Information Fusion in Mobile Crowdsensing

In mobile crowdsensing (MCS), information fusion is necessary to obtain data aggregation results. In information fusion, most of the existing personalized mechanisms only consider meeting the personalized requirements of data collectors and rarely consider the potential personalized requirements of data users. Furthermore, how to provide personalized data aggregation results for data users with different data quality requirements has not been addressed. This paper proposes a personalized privacy-preserving information fusion (P3IF) mechanism based on the personalized sampling mechanism in the MCS. P3IF provides personalized data aggregation results for data users with different data quality requirements while ensuring personalized privacy protection for data collectors. Specifically, we design a personalized privacy-preserving information fusion scheme based on the personalized differential privacy mechanism. Considering on the privacy requirements of the data collectors, we conduct personalized privacy sampling on the raw data from the data collectors and obtain a subset of sensing data. According to the data quality requirements of data users and the quality of each data, the obtained subset is sampled for personalized data quality requirements, and the final data set is obtained. Simulation experiments verify the feasibility and effectiveness of P3IF.