Hiding the Sensitive Itemsets through the Ordered Sensitive Transactions Deletion via Multi-Objective Genetic Algorithms

Association rules are used to find hidden relationships and dependencies among different itemsets in the database that is extracted in the form of the rule, but the problem with this approach is the discovery of sensitive information and the treatment of information privacy. The sanitization process data is considered as a NPHard problem. In this article, we try to reduce support the sensitive itemsets in the transactional database using multi-objective genetic algorithms and the support-based approach. The proposed approach with the transaction deletion that includes sensitive itemsets leads to less support sensitive itemsets than the minimum support threshold and leads to the database sanitization. In each iteration of our method leads to increase the speed and reduce the performance criteria by one time of the scanning of the sensitive transaction instead of scanning the entire database of transactions. In addition, to reduce the effects of hiding the sensitive itemsets, the transactions sort based on the shortest length, the most sensitive itemsets and the least non-sensitive itemsets.