A unified framework of community hiding using symmetric nonnegative matrix factorization

Community detection can help us to deeply understand community structures and reveal potential social relationships among members. However, as people's concerns over the excessive mining of personal information have grown, the idea of community hiding has been proposed for privacy protection. Most existing community hiding methods based on heuristic approaches and genetic algorithms ignore the generative process of the network and cannot provide a better explanation of the rationality of the hiding mechanism. In addition, they are not simultaneously applicable to the global community, target community, or target nodes. In this study, we address the community hiding problem on three scales: global community hiding (macroscopic), target community hiding (mesoscopic), and target node hiding (microscopic). We propose a unified community hiding framework (CH-SNMF) that can be applied to all three scales. The basic idea is to use symmetric nonnegative matrix factorization to describe the network generative mechanism. It has a potential clustering capability that can mine key links and link sets during the network generation process. Therefore, they can be used to disrupt community structures with minimal perturbation budgets. The experimental results show that CH-SNMF outperforms many advanced baseline methods and effectively protects organizational and individual privacy.