Edge–Cloud-Aided Differentially Private Tucker Decomposition for Cyber–Physical–Social Systems

Abstract

Extensive growth in developing new and efficient methods for tensor factorizations has made their intelligent applications in cyber–physical–social systems (CPSS) a hot research topic. Tensor factorizations facilitate the need for recommendations that are accurate and circumstantial, which pushes the limits of traditional collaborative filtering methods to multifaceted versions based on real intelligent environments. Nevertheless, recommenders in edge–cloud computing require information encapsulated in user models to give useful suggestions on user preferred items, which presents stern privacy trepidations. In this article, a novel edge–cloud-aided differentially private tucker decomposition scheme is proposed to avert data owner’s private data from being learned by other data owners, untrusted edge, and cloud during tucker decomposition for CPSS. Our design dissevers users’ private data computations in tucker decomposition to edges from the cloud, and the cloud is forced to perform perturbed results aggregation while preserving privacy. The scheme employs perturbation to ensure differential privacy, and the perturbation noise components are decomposed into small manageable parts that can be locally and independently resolved by edges. Our extensive experiments on two real data sets show the proposed scheme is efficient and has tolerable side effects on the results’ utility.