Solving Sensitive Itemset Hiding Problem by Using Binary Integer Programming Method with Minimal Side Effects
碩士 === 國立東華大學 === 資訊工程學系 === 97 === Mining frequent itemsets from huge amounts of data is an important issue in data mining. The hidden and valuable information can be retrieved for commercial benefits. However, some of the sensitive itemsets have to be hidden in the database for privacy or security...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2009
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/88939265985913585431 |
| Summary: | 碩士 === 國立東華大學 === 資訊工程學系 === 97 === Mining frequent itemsets from huge amounts of data is an important issue in data mining. The hidden and valuable information can be retrieved for commercial benefits. However, some of the sensitive itemsets have to be hidden in the database for privacy or security concern. We investigate the influence of hidden sensitive itemsets in database and minimize the effects to the non-sensitive itemsets. In this thesis, we propose a novel method for sensitive itemsets hiding. By formulating the problem as a constraint satisfaction problem and solving it with binary integer programming, a sanitization database is gotten. Moreover, the victim itemsets from non-sensitive itemsets can be chosen by considering the relationships between sensitive and non-sensitive itemsets. Our approach can retrieve the minimal side effects by relaxation the constraints of the victim itemsets. The experimental results indicate that our approach is efficient for hiding sensitive itemsets.
|
|---|