Anonymous Methods Based on Multi-Attribute Clustering and Generalization Constraints

The dissemination and sharing of data sheets in IoT applications presents privacy security challenges that can be addressed using the k-anonymization algorithm. However, this method needs improvement, for example, areas related to its overgeneralization insufficient attribute diversity constraints during anonymization process. To address these issues, study proposes a multi-attribute clustering generalization (k,l)-anonymization applied multidimensional tables. algorithm first used greedy strategy rank attributes by width first, derived division into dimensions construct hierarchy, then selected with most significant values as priority attributes. Next, k-nearest neighbor (KNN) was introduced determine initial center width-first results, divide quasi-identifier KNN clusters according distance metric, generalize equivalence class hierarchical structure. Then, proposed re-evaluated generalized before each operation. Finally, employed an improved frequency–diversity constraint sensitive order ensure there were at least l records mutually dissimilar closest class. While limiting frequency threshold occurrence attributes, remained similar within group, thus achieving protection anonymity all