A Novel Secure Multiparty Algorithms in Horizontally Distributed Database for Fast Distributed Database

V. Bangaru Lakshmi, R. Murugadoss

Abstract


The proposed a protocol for protected mining of association rules in horizontally distributed database. The current leading set of rules is that of Kantarcioglu and Clifton. Our procedure, like theirs, is based on the Fast Distributed Mining (FDM) algorithm of Cheung et al. which is an unsecured spread version of the Apriori algorithm. The main ingredient in our procedure are two novel secure multi-party algorithms. One that computes the union of private subsets that each of the interacting group of actors hold, and another that tests the inclusion of an element held by one actor in a subset held by another. Our protocol offers improved separation with respect to the protocol. In addition, it is simpler and is extensively more efficient in terms of announcement rounds, announcement cost and computational cost.

Keywords


Privacy Preserving Data Mining; Distributed Computation; Frequent Itemsets; Association Rules

Full Text:

PDF




Copyright (c) 2015 V. Bangaru Lakshmi, R. Murugadoss

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

 

All published Articles are Open Access at  https://journals.pen2print.org/index.php/ijr/ 


Paper submission: ijr@pen2print.org