HVDB: a hierarchical verifiable database scheme with scalable updates

Abstract

The notion of verifiable database (VDB) plays an important role in secure outsourcing of data storage, which allows a client, typically a resource-constraint one, to outsource the large-scale databases to an untrusted server and make retrieval and update queries. For each query request, the server responds with a query result and a proof which is used to verify the result. Plenty of research work has been done on designing efficient VDB schemes in the past years. However, it seems that all of the existing VDB schemes are presented in the amortized model. That is, all existing VDB schemes require a prohibitively expensive pre-processing stage. As a result, the overhead for the initialization algorithm (e.g., the key generation algorithm) is too heavy to afford by the client. Furthermore, VDB schemes can only ensure the integrality of the whole database. However, it is incapable of verifying a segment of the database and localizing the tampered record efficiently when the database is tampered with. In this paper, we firstly propose a new primitive called Vector Commitment Tree (VCT), in which each node is a vector commitment (VC) of its q children. Then, we utilize VCT as a building block to propose a hierarchical verifiable database scheme (HVDB) with scalable updates, which supports the hierarchical verification and the tampered record localization. Besides, HVDB can also greatly reduce the burden of initialization algorithm of VDB schemes. Finally, the analysis and experimental results show that the proposed HVDB scheme can achieve the desired security requirements and improve the efficiency for practical application.