Research on (α,β,l,k)-anonymity Model for Social Network

Abstract

More and more people pay attention to the security problems in social network. We propose a (α,β,l,k)-anonymity model to protect the publishing data security based on the graph structure of social network. It can make anonymous vertexes and edges of graph effectively resist d-neighborhood attack, and structure attack. At the same time, it can make anonymous data of vertexes in social network effectively resist background knowledge attack and homogeneity attack by using the influence matrix of background knowledge, and can solve diversity of vertexes sensitive attribute, meet personalized needs according to the weighted parameter α, β given in advance.