ANALYSIS ON DATA ANONYMIZATION USING L-DIVERSITY & TCLOSENESS
Keywords:
Terms- k-anonymity, data mining, l-diversity, background knowledge, privacy disclosure, t-closenessAbstract
The knowledge analyst processes information by records and analytics. A most common technique of data anonymization developed for privacy protecting statistics publishing. The k-anonymity is the important method which is important method for publishing the microdata k-anonymity should contain k-tuples for a set of records. Numerous authors’ process data that cannot save attribute disclosure. Many varieties of researches were carried out for isolating quasi-identifiers from sensitive attribute. For evaluation of records, information analyzer has to offer safety to be getting attacked. The belief of l-range has been proposed to address this; each equivalence class has l-diversity as minimum l properly-represented values for every sensitive characteristic. So we proposed a privateness belief called tcloseness, then we apply the Earth mover distance degree for t-closeness. We explain for the method t-closeness. Finally, we have two approaches which are an anonymization system and a reconstruction process. This method provides overview on popular information protecting techniques. On this examine, concepts behind those strategies are analyzed and explained with illustration.
