Privacy Preserving Association Rules Mining Based on Data Disturbance and Inquiry Limitation

Abstract

Privacy is an important issue in data mining and knowledge discovery. In this paper, we use the randomized response technology to conduct association rule mining. We propose a privacy preserving association rule mining algorithm which is called DDIL based on data disturbance and inquiry limitation. Applying DDIL on the data set, the original data can be disturbed and hidden and the degree of privacy-preserving is improved effectively. Specially, a high effective method of generating frequent items from transformed data sets is proposed. Our experiments demonstrate that when the random parameters are chosen suitably, our methods are effective and provide acceptable values in practice for balancing privacy and accuracy.