Utility-Friendly Heterogenous Generalization in Privacy Preserving Data Publishing

K-anonymity is one of the most important anonymity models that have been widely investigated and various techniques have been proposed to achieve it. Among them generalization is a common technique. In a typical generalization approach, tuples in a table was first divided into many QI(quasi-identifier)-groups such that the size of each QI-group is larger than K. In general, utility of anonymized data can be enhanced if size of each QI-group is reduced. Motivated by this observation, we propose linking-based anonymity model, which achieves K-anonymity with QI-groups having size less than K. To implement linking-based anonymization model, we propose a simple yet efficient heuristic local recoding method. Extensive experiments on real data sets are also conducted to show that the utility has been significantly improved by our approach compared to the state-of-the-art methods.