Enhancement of Data Utility for Data Anonymization - A Review

A key challenge in privacy-preserving data mining is maximizing the usage of data by minimizing the privacy risk. The organization provides the data that must be both useful and also with contains low risk of confidentiality disclosure is the main aim. The Concept of recognizing the de-identification of data is generally inadequate to protect their confidentiality against attacker so, disclosure limitation techniques can be used to the original data to reduce the risk. Desirably, the resulting restricted data have both high data utility to users (analytically valid data) and low disclosure risk (safe data). The organization applies a set of transformation to the original data before accessing it. This study aims to examine an approach to permit dissemination of explicit data to a wider range or data utility of public constituents and at the same time protects the identities of original data. In this paper maximization of the data utility is addressed by maintaining its risk below a certain acceptable threshold.