A Clustering Bipartite Graph Anonymous Method for Social Networks

摘要

Privacy preserving in social networks has been raised serious concerns in recent years. One of the privacy disclosures is brought about through structural attacks by malicious users. In this paper, we consider the privacy preserving publication against sensitive edges identification attacks in social networks, which are expressed by bipartite graphs. Firstly, we present a positive one-way (c_1, c_2)-security algorithm, a negative one-way (c_1, c_2)-security algorithm, and a two-way (c_1, c_2)-security algorithm. The proposed algorithms are based on the k-security group theory and the sensitive edges identification attacks in social networks. Furthermore, a bipartite graph anonymous problem is formally defined to against sensitive edges identification attacks. Meanwhile, a clustering-based bipartite graph anonymous method, Clustering-based bipartite (c_1, C2)-security algorithm (CBB(c_1, c_2)-security), is proposed. The experimental results show that under the equal conditions, our method not only produces less information loss than that of the existing method, but also effectively resists sensitive edges identification attacks and realize security release of bipartite graphs.