Data Transformation and Data Transitive Techniques for Protecting Sensitive Data in Privacy Preserving Data Mining

Abstract

Privacy Preserving Data mining is a new research area in the field of data mining. It greatly deals with the side effects of the data mining techniques. With the help of data mining techniques people can analyze and extract the hidden patterns from the large data set. In many situations, the retrieved hidden knowledge provides the confidential information. This confidential information may be misused for variety of purposes. This situation raises the need for privacy and security issues. The main objective of privacy preserving data mining is, extracting the knowledge available in the data; at the same time the individual’s privacy should be protected. It also protects the data owner against mishandling or disclosure of the data. Several techniques and algorithms are required for maintaining the secrecy of data in order to limit the extraction of confidential patterns. There are many techniques are available for protecting the sensitive data in the database. Some of them are statistical, cryptographic, randomization methods, k-anonymity model, l-diversity and etc [2–5, 7]. In this research work, we have developed two new perturbative masking techniques known as data transformation technique and data transitive technique. These techniques are used for protecting sensitive data in the form of modifying the sensitive data. In order to find the best technique, we have compared the two techniques with the existing technique micro aggregation. Experimental result shows that the data transformation technique gives the better result.