Protecting Frequent Item sets Disclosure in Data Sets and Preserving Item Sets Mining
The main approach to hide sensitive frequent itemsets is to reduce the support of each given sensitive itemsets. This is done by modifying transactions or items in the database. However, the modifications will generate side effects, i.e., non-sensitive frequent itemsets falsely hidden (the loss itemsets) and spurious frequent itemsets falsely generated (the new itemsets). There is a trade-off between sensitive frequent itemsets hidden and side effects generated. Furthermore, it should always take huge computing time to solve the problem. In this paper, the authors propose a novel algorithm, FHSFI, for fast hiding Sensitive Frequent Itemsets (SFI).