A robust privacy preserving model for data publishing

Data publishing for analysis by maintaining individual privacy when it contains sensitive attributes is a problem of increasing significance today. So, preserving sensitive data without experiencing serious attacks is the greatest challenge in the field of privacy preserving data publishing. The existing privacy models are experiencing one or the other type of attacks which leads to privacy breach. In this paper, we are proposing a new privacy preserving model, which minimizes attacks and overcomes drawbacks experienced by existing popular anonymizing approaches. Our technique is inspired from two of the popular techniques such as primarily, Closeness approach which was proposed by Ninghui in 2012. t-closeness requires that the distribution of a sensitive attribute in any equivalence class is close to the distribution of that attribute in the overall table i.e., the distance between the two distributions should be no more than a threshold t. But it was subjected its own limitations. And the second technique, “p-sensitive, k- anonymity” proposed by Truta and Vinay in 2006, which reduces information loss by increasing utility. Our technique includes features combining these two techniques which lead to an efficient model. Experimental results show that our privacy measure runs faster and significantly reduce the privacy breach by overcoming many of the attacks faced by existing models in the literature.