PROJECT TITLE:

Privacy-Preserving Outsourced Association Rule Mining on Vertically Partitioned Databases - 2016

ABSTRACT:

Association rule mining and frequent itemset mining are two standard and widely studied information analysis techniques for a vary of applications. In this paper, we specialise in privacy-preserving mining on vertically partitioned databases. In such a situation, knowledge house owners want to learn the association rules or frequent itemsets from a collective data set and disclose as little information about their (sensitive) raw data as potential to alternative knowledge owners and third parties. To guarantee data privacy, we design an efficient homomorphic encryption theme and a secure comparison scheme. We then propose a cloud-aided frequent itemset mining solution, which is employed to build an association rule mining solution. Our solutions are designed for outsourced databases that allow multiple data owners to efficiently share their information securely without compromising on knowledge privacy. Our solutions leak less information regarding the raw data than most existing solutions. In comparison to the sole known resolution achieving an analogous privacy level as our proposed solutions, the performance of our proposed solutions is 3 to 5 orders of magnitude higher. Based on our experiment findings using completely different parameters and data sets, we have a tendency to demonstrate that the run time in each of our solutions is only one order over that in the simplest non-privacy-preserving knowledge mining algorithms. Since both data and computing work are outsourced to the cloud servers, the resource consumption at the info owner end is very low.