A general framework for privacy preserving data publishing

Data publishing is an easy and economic means for data sharing, but the privacy risk is a major concern in data publishing. Privacy preservation is a major task in data sharing for organizations like bureau of statistics, hospitals, etc. While a large number of data publishing models and methods have been proposed, their utility is of concern when a high privacy requirement is imposed. In this paper, we propose a new framework for privacy preserving data publishing. We cap the belief of an adversary inferring a sensitive value in a published data set to as high as that of an inference based on public knowledge. The semantic meaning is that when an adversary sees a record in a published data set, s/he will have a lower confidence that the record belongs to a victim than not. We design a method integrating sampling and generalization to implement the model. We compare the method with some state-of-the-art methods on privacy-preserving data publish∗Corresponding author Email addresses: [email protected] (A.H.M. Sarowar Sattar), [email protected] (Jiuyong Li) 1School of Information Technology and Mathematical Science, Mawson Lakes, SA-5095. Mob. +61420863356 2D3-07, School of Information Technology and Mathematical Science, Mawson Lakes, SA5095. Preprint submitted to Elsevier October 22, 2013 ing experimentally, our proposed method provides sound semantic protection of individuals in data and, provides higher data utility.