DATA PRIVACY IN ENCRYPTED RELATIONAL DATA USING K-NN CLASIFICATION

Abstract

Data Mining has wide applications in various domains, for instance, keeping cash, arrangement, intelligent research and among government workplaces. Portrayal is one of the usually used assignments in data mining applications. As far back as decade, due to the climb of various assurance issues, various theoretical and convenient responses for the request issue have been proposed under different security models. In any case, with the present pervasiveness of circulated processing, customers now have the opportunity to outsource their data, fit as a fiddle, and moreover the data mining endeavors to the cloud. Since the data on the cloud is in encoded outline, existing security protecting plan procedures are not significant. In this paper, we focus on dealing with the gathering issue over encoded data. In particular, we propose a secured k-NN classifier over mixed data in the cloud. The proposed tradition guarantees the characterization of data, security of customer's information question, and covers the data get to outlines. To the best of our knowledge, our work is the first to develop an ensured kNN classifier over encoded data under the semi-authentic model. In like manner, we observationally inspect the profitability of our proposed tradition using a bona fide dataset under different parameter settings.