Authentication of spatio-textual similarity join queries in untrusted cloud environments: Authentication of spatio-textual similarity join queries

In this paper, we study the problem of authentication of spatio-textual similarity join queries in untrusted cloud environments. To solve this problem, we first propose a pairwise authentication scheme, where object pairs are considered as basic processing units. In this scheme, an object hash tree is proposed for the data owner (DO) to build the authenticated data structure (ADS) over the data collection. Moreover, during join processing, a pair table is introduced for the service provider (SP) to construct the verification object (VO) for client's authentication. However, when clients authenticate the join results, they have large number of pairs to examine, which leads to excessive computation cost. Therefore, we then propose an optimized MR*-tree-based scheme. In this scheme, the DO spatially organizes the objects in an ADS called MR*-tree, which combines the concepts of the Merkle hash tree and the R*-tree. Based on the MR*-tree, the SP employs the depth-first search strategy to find the join results and constructs the VO according to the visited nodes of the MR*-tree. Our extensive experiments on the real-world dataset verify the effectiveness and efficiency of our proposed schemes on several performance metrics, including the data preprocessing time, running time, VO size, and authentication time. Copyright (C) 2016 John Wiley & Sons, Ltd.