Confidentiality of data or resources is of primary importance in Privacy Preserving Data Mining (PPDM) Systems. The research work presented through this paper discusses the PPDM model in which the privacy of data transacted amongst the various Data Custodians involved is highlighted. The data available with each data custodian is assumed to be horizontally portioned. The proposed model considers the C5.0 algorithm for data mining and classification rule generation due to its advances and classification accuracy over its predecessors. Privacy of the data transacted or secure multiparty computation is achieved by using the commutative RSA cryptography scheme. The proposed model is compared with the existing secure group communication techniques like Secure Lock and Asynchronous Control Polynomial in terms of computational efficiency. Furthermore the privacy preserving feature of the proposed scheme is proved in terms of the computational indistinguishablity of the data transacted amongst the varied data custodians involved discussed in the paper.
The aim of the research work is to mine the data set available with each custodian in a semi honest model, securely without disclosure of any data amongst various custodians involved. No custodian discloses any information. In the proposed scheme in order to reduce the computational complexity, the data partitioning has been done in the horizontal way. The proposed research work consists of a well skilled and planned architecture implementation for achieving the proposed privacy preservation in the data mining filed and used a new hybrid data mining model which is developed for combining commutative RSA and a C5.0 algorithm to generate classification rules. This study utilized real world data collected from an UCI repository and experiments are conducted based on the parameters like time complexity, accuracy and error rate. The proposed model preserve expected level of privacy without any information loss, take less time for computation, lower error rate and improves accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.