Accelerated search over encrypted cloud data

Abstract

Companies and other organizations such as hospitals seek more and more to enjoy the benefits of cloud computing in terms of storage space and computing power. However, outsourced data must be encrypted in order to be protected against possible attacks. Therefore, traditional information retrieval systems (IRS) are no longer effective and must be adapted in order to work over encrypted cloud data. In addition, in order to provide the ability to search over an encrypted index, we use the vector model to represent documents and queries which is the most used in the literature. During the search process, the query vector must be compared with each document vector which is a time consuming process since the data collection is generally huge. Consequently, the search performance is degraded and the search process is too slow. To overcome this drawback, we propose the use of High Performance Computing (HPC) architectures to accelerate the search over encrypted cloud data. Indeed, we propose several techniques that take benefit from Graphics Processing Unit (GPU) and computer cluster architectures by distributing the work between different threads. In addition, in order to get the best performance, we design our solutions so that they can process several queries simultaneously. The experimental study using 400.000 documents demonstrates the efficiency of our proposals by reaching a speed-up around 46×.