Abstract
With large growth in technology, reduced cost of storage media and networking enabled the organizations to collect very large volume of information from huge sources. Different data mining techniques are applied on such huge data to extract useful and relevant knowledge. The disclosure of sensitive data to unauthorized parties is a critical issue for organizations which could be most critical problem of data mining. So Privacy preserving data mining (PPDM) has become increasingly popular because it solves this problem and allows sharing of privacy sensitive data for analytical purposes. A lot of privacy techniques were developed based on the k-anonymity property. Because of a lot of shortcomings of the k-anonymity model, other privacy models were introduced. Most of these techniques release one table for research public after they applied on original tables. In this paper the researchers introduce techniques which publish more than one table for organizations preserving individual's privacy. One of this is (alpha, k) -anonymity using lossy-Join which releases two tables for publishing in such a way that the privacy protection for (alpha, k)-anonymity can be achieved with less distortion, and the other one is Anatomy technique which releases all the quasi-identifier and sensitive values directly in two separate tables, met l-diversity privacy requirements, without any modification in the original table.