Privacy-Assured Similarity Query over Graph-Structured Data in Mobile Cloud

In the emerging mobile cloud paradigm, more and more innovative social applications are provided. The data of these applications is usually represented by the graph structure. For effective data retrieval, it is a crucial requirement to enable substructure similarity query over these graphstructured data. The sensitive information of the graphs and users may be leaked during the retrieval, leading to privacy violations. However, most existing works on protecting privacy pay little attention to this problem. Additionally, considering the complicated similarity computation and the privacy requirements, it is particularly challenging to solve the problem effectively. In this paper, for the first time, we investigate the problem of privacy-assured substructure similarity query over graph-structured data in mobile cloud. Our solution proposes a series of secure algorithms to effectively perform the similarity query without privacy breaches. The proposed solution first builds a secure feature-graph index to represent the featurerelated information about each data graph based on privacy homomorphism and obscuration methods, and then calculates the similarity between the query graph and each data graph by the difference of feature frequency in a privacy-preserving manner. Thorough analysis is given to investigate privacy and efficiency guarantees, and the experiments further demonstrate the validity and efficiency of the proposed solution.