Personalized Privacy Protection Method for Sensitive Temporal Data

Abstract

Crowd sensing, as a new paradigm for perception data collection, has been widely applied. However, in the process of constructing a knowledge graph for group intelligence perception networks, attackers can use the correlation of participant temporal data to reconstruct participant related information, resulting in privacy leakage. A participant sensitive temporal data privacy protection method(PSTDPP) based on localized differential privacy is proposed to address this issue. Firstly, we use a knowledge graph to construct a sensitive temporal data relationship network and explore the correlation between temporal data background knowledge. Secondly, by combining attention mechanisms and mutual information ideas, a privacy model for participant submitted data and an availability model for perceived data are constructed, and personalized local differential privacy is used to solve the problem of graph data availability under privacy budget constraints. The simulation results show that the proposed method can effectively prevent the privacy leakage problem of sensitive temporal data, and can achieve a good balance between privacy protection level and data availability.