Date of Publication :7th April 2016

Abstract: Data mining is widely used in numerous areas such as banking, medicine, scientific research and various other government applications. Data Classification is most extensively used task in data mining applications. The rise of various issues in privacy has led to several solutions to this problem. However, with the increased fame of cloud computing, users can now outsource their data onto the cloud in an encrypted form, as well as perform the required mining tasks on the cloud. Since the data is in an encrypted form on the cloud, existing privacy-preserving classification techniques are not suitable. In this paper, we focus on a viable technique to perform data classification using k-NN classifier over the encrypted data and secure the confidentiality of data, privacy of the user’s input query and also hide the data access patterns. We also analyze the efficiency of the proposed protocol empirically.

Reference :