Paper Details

Data mining is used to extract important knowledge from large datasets, but sometimes these datasets are splitamong various parties.Privacy liability may prevent the parties from directly sharing the data and some types ofinformation about the data.This paper presents different methods for secure mining of association rules in horizontallydistributed databases. The main aim of this paper is protocol for secure mining of association rules in horizontallydistributed databases. The current main protocol is that of Kantarcioglu and Clifton. This protocol, like theirs, is basedon the Fast Distributed Mining (FDM) algorithm of Cheung et al., which is an unsecured distributed version of theApriori algorithm. The main components in this protocol are two novel secure multi-party algorithms — one thatcomputes the union of private subsets that each of the interacting players hold, and another that tests the inclusion of anelement held by one player in a subset held by another. This protocol offers improved privacy with respect to the protocolin. In addition, it is simpler and is significantly more efficient in terms of communication rounds, communication costand computational cost.

Ms. Shweta Gandevia, Mr. Mohit Patel, “Survey Paper on Secure Data Mining for Horizontally Distributed DataBase”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 3, Issue 2, pp. 174-178, February 2016.