Privacy Model for Anonymizing Sensitive Data in Social Network

Abstract- With the rapid growth of social networks, more researchers found that it is a great opportunity to obtain useful information from the social network data, such as the user behavior, community growth, disease spreading, etc. However, it is paramount that the published social network data should not reveal the private information of individuals. Recently, researchers have developed privacy models to prevent node reidentification through structure information. Even when these privacy models are enforced, an attacker may still be able to infer one’s private information if a group of nodes largely share the same sensitive labels (i.e., attributes), because the label-node relationship is not well protected by pure structure anonymization methods. Existing approaches, which rely on edge editing or node clustering, may significantly alter key graph properties. In our project, k-degree-l-diversity anonymity model is defined, that considers the protection of structural information as well as sensitive labels of individuals. Along with this, a novel anonymization methodology is proposed based on adding noise nodes into the original graph with the consideration of introducing the least distortion to graph properties. And, a rigorous analysis on the theoretical bounds on the number of noise nodes added and the effectiveness of the proposed technique is conducted