A Case Study on Mining Security Issues & Remedies in Privacy Preservation

Abstract

The development in data mining technology brings serious threat to the individual information. The objective of privacy preserving data mining (PPDM) is to safeguard the sensitive information contained in the data. The unwanted disclosure of the sensitive information may happen during the process of data mining results. In this study we identify four different types of users involved in mining application i.e. data source provider, data receiver, data explorer and determiner decision maker. We differentiate each type of user's responsibilities and privacy concerns with respect to sensitive information. We'd like to provide useful insights into the study of privacy preserving data mining. This paper presents a comprehensive noise addition technique for protecting individual privacy in a data set used for classification, while maintaining the data quality. We add noise to all attributes, both numerical and categorical, and both to class and non-class, in such a way so that the original patterns are preserved in a perturbed data set. Our technique is also capable of incorporating previously proposed noise addition techniques that maintain the statistical parameters of the data set, including correlations among attributes. Thus the perturbed data set may be used not only for classification but also for statistical analysis.