A Novel Approach Of Privacy Preserving Data With Anonymizing Tree Structure

Abstract

Data anonymization techniques have been proposed in order to allow processing of personal data without compromising user’s privacy. the data management community is facing a big challenge to protect personal information of individuals from attackers who try to disclose the information. So data anonymization strategies have been proposed so as to permit handling of individual information without compromising user’s privacy. Data anonymization is a type of information sanitization whose intent is privacy protection. It is the process of either encrypting or removing personally identifiable information from data sets, so that the people whom the data describe remain anonymous. We are presenting k(m;n)-anonymity privacy guarantee which addresses background knowledge of both value and structure using improved and automatic greedy algorithm. (k (m,n) - obscurity ensure) A tree database D is considered k (m,n) - unknown if any assailant who has foundation information of m hub names and n auxiliary relations between them (ancestor descendant), is not ready to utilize this learning to distinguish not as much as k records in D. A tree dataset D can be transformed to a dataset D0 which complies to k (m,n) - anonymity, by a series of transformations.The key idea is to replace rare values with a common generalized value and to remove ancestor descendant relations when they might lead to privacy breaches.