Resolving Multiparty Privacy Conflicts in Social Media

On-line social networks like Facebook are increasingly utilized by many people. These networks allow users to publish their own details and enable them to contact their friends. Some of the information revealed inside these networks is private. These structures allow clients to present specific of them and interface with their mates. Client profile and family relationship relations are really private. These networks allow users to publish details about themselves and to connect to their friends. Some of the information revealed inside these networks is meant to be private. A privacy breach occurs when sensitive information about the user, the information that an individual wants to keep from public, is disclosed to an adversary. Private information leakage could be an important issue in some cases. And explore how to launch inference attacks using released social networking data to predict private information. In this we map this issue to a collective classification problem and propose a collective inference model. In our model, an attacker utilizes user profile and social relationships in a collective manner to predict sensitive information of related victims in a released social network dataset. To protect against such attacks, we propose a data sanitization method collectively manipulating user profile and friendship relations. The key novel idea lies that besides sanitizing friendship relations, the proposed method can take advantages of various data-manipulating methods. We show that we can easily reduce adversary's prediction accuracy on sensitive information, while resulting in less accuracy decrease on non-sensitive information towards three social network datasets. To the best of our knowledge, this is the first work that employs collective methods involving various data-manipulating methods and social relationships to protect against inference attacks in social networks.