A verifiable and privacy‐preserving multidimensional data aggregation scheme in mobile crowdsensing

Abstract

AbstractMobile crowdsensing has become a popular data collection paradigm and has been extensively studied. Since the analysis of sensory data usually reveals privacy of mobile users, data aggregation technology is widely used to avoid privacy disclosure. However, traditional privacy‐preserving data aggregation schemes cannot provide aggregate statistics of multidimensional data in fine‐grained areas or resist collusive attacks. Moreover, the cloud platform is not fully trusted, and it is challenging to verify the correctness of data aggregation results. To provide privacy‐preserving multidimensional statistics within fine‐grained areas and verify results of data aggregation, we propose a verifiable privacy‐preserving data aggregation scheme in this article, which is based on data double‐masking, Shamir's secret sharing, and bilinear mapping. Specifically, a key agreement is utilized to establish mask seeds for users, while the users are required to extend mask values and generate the verification key with bilinear mapping. The cloud platform aggregates masked data and provides proof of computational results. Theoretical analysis demonstrates our scheme can protect data and location privacy, verify the aggregation results, and improve the rubustness to failure. The simulation results show that the computational overhead of mobile devices by using the proposed anticollusion scheme is better than that of homomorphic encryption. In addition, the computational complexity of task requesters is less than that of the PVPA scheme for verification of multidimensional aggregation results.