An anonymized method for classification with weighted attributes
Jiandang Wu, Jiyi Wang, Jianmin Han, Hao Peng, Jianfeng Lu · 2013
K-anonymity is an effective method to protect individual's privacy for microdata publishing. However, the existing anonymity methods do not consider how to mask data for a specific application. This paper proposes an anonymity method for classification with weighted attributes. The method first evaluates the weight of each attribute for classification, then proposes an attribute weighted Bottom-Up k-anonymity algorithm which generalizes large weighted attributes as weakly as possible. The experiment results show that the method can get higher quality anonymous data for classification mining.