关键词: 社交网络, 推理攻击, 隐私保护, 机器学习

Abstract:

Nowadays, social network platforms such as Weibo and Twitter are widely used to communicate, create online communities, and conduct social activities. The content posted by users can be inferred from a large amount of privacy information, which has led to the rise of privacy inference technology for users in social networks. By using knowledge such as the user’s text content and online behaviors, inference attacks can be performed on users. Social relationship inference and attribute inference are two basic attacks on social network user privacy. The research on the mechanism and method of inference attack protection is also increasing, this paper classifies and summarizes the research and literature related to privacy inference and protection technology. Finally, it discusses and prospects the privacy inference and protection in social networks.

Key words: social networks, inference attacks, privacy protection, machine learning