An Integer Linear Programming Scheme to Sanitize Sensitive Frequent Itemsets

Abstract

In this paper, we propose a novel approach to address the frequent item set hiding problem, by formulating it as an integer linear program (ILP). The solution of the ILP points out the transactions that need to be sanitized in order to achieve the hiding of the sensitive frequent item sets, while the impact on other non-sensitive item sets is minimized. We present a novel heuristic approach to calculate the coefficients of the objective function of the ILP, while at the same time we minimize the side effects introduced by the hiding process. We also propose a sanitization algorithm that performs the hiding on the selected transactions. Finally, we evaluate the proposed method on real datasets and we compare the results of the newly proposed method with those of other state of the art approaches.