Integer Linear Programming Approach for Hiding Sensitive Association Rules

The privacy preserving data mining plays a vital role in statistical agencies and database privacy investigations, which are concerned with preserving secrecy disclosure during data mining. The large-sized dataset contains sensitive association rules, which are required to be hidden from unauthorized users. Thus, association rule hiding is a competent solution that helps enterprises keeps away from the hazards caused by sensitive knowledge leakage when sharing the data in their collaborations. This paper presents a constraint based optimization model for concealing sensitive association rules through the formulation of a well-defined Integer Linear Programming (ILP). The developed method reduces the database sanitization problem to a Constraint Satisfaction Problem, which is solved using ILP. Sanitization algorithm performs hiding of sensitive rules by reducing the support or the confidence of the sensitive rules. The results of the experimental evaluation of the proposed approach on real-life datasets indicate the promising performance of the approach in terms of side effects on the original database.