New Approach for Sensitive Association Rule Hiding
Xiaoming Zhang, Xi Qiao · 2008
A new sensitive rule hiding algorithm, including two processes of weak association transaction adding and strong association transaction removing, is presented based on the devotion degree of transactions to the discovered association rules. The approach and algorithm are stated in detail aiming to hide simple rules,including two types of single rule and composed rule.Four item modification methods are designed for the updating of selected weak association transactions. Only a small number of transactions are required in updating to keep the original features in the mined dataset. When the modification factor is set above 0.05, the hiding rate can be reached to 100%, and the side effects of the lost rules and new created rules are very small with rate less than 10%. Finally, after the hiding detection to the new database, the robustness to the support attack is satisfying with suitable hiding rate.