Modeling the Uncertain Data in the K-anonymity Privacy Protection Model

Modeling is the basis for data management of uncertainty. The Specificity in the uncertainty of the data in the k-anonymity privacy protection model is found, namely, its uncertainty is caused by human with generalization, the probability that each instance after generalization is reduced to the original tuple is equal. The past modeling approaches of uncertainty data are not suitable for this kind of uncertainty data simply. In order to describe it, several new modeling methods are proposed in this paper: K_attr model uses attribute-ors ways to describe the uncertainty of the quasi-identifier attribute values, K_tuple model takes the quasi-identifier attribute values as nest relations and use tuple-ors ways to describe the relations, K_upperlower model separates a quasi-identifier attribute to two fields: upper and lower, K_tree model converts each quasi-identifier attribute into a tree. The completeness and closure of these models are discussed later.