Introduction

Related works

Preliminary

Trust evaluation based on the combination of evidence

Experiment and analysis

Conclusion

References

Abstract

Trust is an important criterion for access control in the field of online social networks privacy preservation. In the present methods, the subjectivity and individualization of the trust is ignored and a fixed model is built for all the users. In fact, different users probably take different trust features into their considerations when making trust decisions. Besides, in the present schemes, only users’ static features are mapped into trust values, without the risk of privacy leakage. In this article, the features that each user cares about when making trust decisions are mined by machine learning to be User-Will. The privacy leakage risk of the evaluated user is estimated through information flow predicting. Then the User-Will and the privacy leakage risk are all mapped into trust evidence to be combined by an improved evidence combination rule of the evidence theory. In the end, several typical methods and the proposed scheme are implemented to compare the performance on dataset Epinions. Our scheme is verified to be more advanced than the others by comparing the F-Score and the Mean Error of the trust evaluation results.

Introduction

Online social networks (OSNs) are platforms or systems that people can interact with others by sharing or posting blogs online.1 Social networking is very common, such as Facebook, Tweeter, Weibo and CyVOD.2 These platforms provide a free space for everyone to unleash their mind and thoughts. However, it makes information leakage possible.3 The spammers spread malicious links and annoying messages to OSN users without target, and privacy information is unsafe for the cheating actions4 and blackmails.5 To prevent the malicious activities, many schemes such as Access Control6 and digital rights protection7–۹ are proposed. In these schemes, trust degree is usually viewed as the main criterion for security policies to make the privacy management more feasible and effective. As it is important to privacy preservation in OSNs, trust evaluation has become a research focus in recent years.10–۱۳ Researchers try to find the relationship between user features and trust decision. It is no doubt that trust decision is not only affected by objective features of each user but also affected by the subjective options of the user. For example, some people think the one who has a lot of fans in the OSNs is trustworthy, while others would rather choose the people who have higher credit or reputation. So, just a single model without individualization is insufficient to evaluate trust degree between users in OSNs.