Абстрактный

A Robust Slicing Technique for privacy preserving of medical data store

Rachitha M.V, Aparna R , Ruma Panda , Nandita Yambem

Recent works has shown that several anonymization techniques, like generalization and bucketization, have been designed for privacy preserving microdata publishing. Generalization loses considerable amount of information, especially for high-dimensional data. Bucketization does not prevent membership disclosure and is not applicable for data that do not have a clear separation between quasi-identifying attributes and sensitive attributes. In this paper, we present a new slicing technique, which partitions the data both horizontally and vertically and preserves better data utility than generalization and can be used for membership disclosure protection. Another important advantage of the slicing technique is that it can handle high-dimensional data. The new slicing technique can be used for attribute disclosure protection and an efficient algorithm is developed for computing the sliced data that obey the ��?- diversity requirement. Our experiments confirm that the new slicing technique preserves better utility than generalization and is more effective than bucketization in workloads involving the sensitive attribute and also demonstrate that it can be used to prevent membership disclosure