European Journal of Molecular & Clinical Medicine

Abstract

Maintaining privacy in data publishing is a major challenge. In complex world sensitive information privacy is the main issue. Many algorithms are used to protect sensitive information in mined data which is not efficient because resulted output can be easily linked with public data so it shows user identity. Many techniques are used to protect privacy in data mining. Anatomization approaches aim to avoid directly use of sensitive data. The growing popularity and development of anatomization technologies bring sensitive data and protect the security of sensitive information Anatomization. The anatomization approach dissociates the correlation observed between the quasi identifier attributes and sensitive attributes and yields two separate tables with non-overlapping attributes. In the slicing algorithm, vertical partitioning does the grouping of the correlated sensitive attributes in sensitive table together and thereby minimizes the dimensionality. Consequently, it becomes increasingly important to preserve the privacy of published data. An attacker is apt to identify an individual from the published tables, with attacks through the record linkage, attribute linkage, table linkage or probabilistic attack. Two comprehensive sets of real-world relationship data are applied to evaluate the performance of our anonymization approach. Simulations and privacy analysis show our scheme possesses better privacy while ensuring higher utility.