An Enhanced Clustering-Based (k, t)-Anonymity Algorithm for Graphs

Abstract

As people become increasingly reliant on the Internet, securely storing and publishing private data has become an important issue. In real life, the release of graph data can lead to privacy breaches, which is a highly challenging problem. Although current research has addressed the issue of identity disclosure, there are still two challenges: First, the privacy protection for large-scale datasets is not yet comprehensive; Second, it is difficult to simultaneously protect the privacy of nodes, edges, and attributes in social networks. To address these issues, this paper proposes a $(k,\ t)$-graph anonymity algorithm based on enhanced clustering. The algorithm uses $k$-means++ clustering for $k$-anonymity and $t$-closeness to improve $k$-anonymity. We evaluate the privacy and efficiency of this method on two datasets and achieved good results. This research is of great significance for addressing the problem of privacy breaches that may arise from the publication of graph data.