Abstract
With the rapid development of social networks, users pay more and more attention to the protection of personal information. However, the transmission of users’ personal information through social networks will inevitably lead to privacy leakage and make users attacked. A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks. Social relationship inference and attribute inference are two basic attacks on users’ privacy in social networks. This is the first systematic review of privacy inference attacks in social networks. The purpose of this retrospective study is to provide a global summary, summarizing the time trend of the topic, and show the evolution of the topic in the past 15 years. In addition, this paper discusses the trend and development of this topic and finally looks forward to future work. The contribution of our work is helpful for researchers to continue their research in this field.
Highlights
The social network provides a simple platform for people to communicate and interact around the world
The contributions of this paper are as follows: 1) This is the first systematic review of privacy inference in social networks, which provides a review of social network inference and fills the gap; 2) We classify privacy inference attacks by method, compare the technologies and datasets used in these works; 3) We analyze the trend of existing methods, the further research of this field is discussed and prospected
The study [24] used five classification algorithms based on machine learning and three regression algorithms (logistic regression, k-nearest neighbour classification (KNN), classification and regression tree (CART), artificial neural network (ANN) and a support vector machine) to infer attributes, the accuracy is more than 90%
Summary
The social network provides a simple platform for people to communicate and interact around the world. Research shows that users' privacy information can still be inferred from their published content, behaviour, and various auxiliary information, including privacy attributes, social relations, and geographical location [4]. Our work provides a continuous review of inference attack methods and classifies inference attacks into three categories: for user attributes, for geographical location and for social relationships. The contributions of this paper are as follows: 1) This is the first systematic review of privacy inference in social networks, which provides a review of social network inference and fills the gap; 2) We classify privacy inference attacks by method, compare the technologies and datasets used in these works; 3) We analyze the trend of existing methods, the further research of this field is discussed and prospected. The details of all methods will be given in the few sections
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
