Title: Hiding personalised anonymity of attributes using privacy preserving data mining
Authors: N. Rajesh; A. Arul Lawrence Selvakumar
Addresses: Department of MCA, Sir MVIT, Bangalore, India; School of Computer Science and Engineering, Bharathiyar University, Coimbatore, Tamil Nadu, India ' Department of Computer Science, Rajiv Gandhi Institute of Technology, Bangalore, India
Abstract: Privacy preserving data mining (PPDM) is a new direction in the area of data mining, where privacy preserving techniques have been applied to maintain the data privacy. Example through the process of data mining the sensitive data of an individual can be inferred as well as personal information and patterns from non-sensitive data. PPDM (Rajesh and Selvakumar, 2014) based on enumeration and concatenation of attributes using k-anonymity where, the original data is combined using only two attributes to show encrypted one quasi-identifier. So, we proposed a new approach called hiding personalised anonymity for enumerating and concatenating of attributes using PPDM for combination of three attributes to show encrypted one quasi-identifier. We can reconstruct the attributes using encrypted attribute. In this work, we proposed PPDM for combination of three attributes and two level encrypting methods in order to protect the more secure personal information for avoiding sensitive issues using unlimited records.
Keywords: privacy preserving data mining; PPDM; encryption; privacy protection; privacy preservation; personalised anonymity; attributes; cryptography; personal information; information security.
DOI: 10.1504/IJAIP.2015.073717
International Journal of Advanced Intelligence Paradigms, 2015 Vol.7 No.3/4, pp.394 - 402
Received: 12 Nov 2014
Accepted: 01 May 2015
Published online: 16 Dec 2015 *