SVD based Data Transformation Methods for Privacy Preserving Clustering

Nowadays privacy issues are major concern for many government and other private organizations to delve important information from large repositories of data. Privacy preserving clustering which is one of the techniques emerged to addresses the problem of extracting useful clustering patterns from distorted data without accessing the original data directly. In this paper two hybrid data transformation methods are proposed for privacy preserving clustering in centralized database environment based on Singular Value Decomposition (SVD). In hybrid method one, SVD and rotation data perturbation are used as a combination to obtain the distorted dataset. In hybrid method two, SVD and independent component analysis are used as a combination to obtain the distorted dataset. In SVD the data is analyzed in different perspectives to retain important information. Higher order statistics which contains more important information is utilized in independent component analysis. Experimental results demonstrate that the proposed methods are efficiently protects the private data of individuals and retains the important information for clustering analysis.