Abstract
With the rapid development of Online Social Networks (OSNs), OSNs have become a rewarding target for attackers. One particularly representative attack is the Sybil attack, Sybil accounts create a lot of malicious activities, which poses a serious threat to the safety of normal users. Many existing Syibl detection mechanisms have preconditions or assumptions, for example, limiting the number of attacking edges. But in general, the assumption is only a handful, often does not hold in real life scenarios. When the assumption is not established, these mechanisms perform poorly. In this work, We propose a scheme that uses victim prediction to improve Sybil detection accuracy. And our solution does not need to be based on any assumptions. First, we designed a victim classifier to predict victims. Then, based on the prediction results, the edge weights in the graph model are modified. Next, trust propagation is performed on the graph model. Finally, sorting all accounts. The experimental results show that our scheme can ensure that the majority of normal users rank higher than Sybils, thus classifying normal users and Sybils.
Highlights
In recent years, Online Social Networks (OSNs) have emerged as important platforms for people to communicate across the globe
As the influence and popularity OSNs have increased, A large number of attackers have focused their attention on OSNs. [5], [9], [13], [21], they create a large number of fake identities or hijack a large number of existing legitimate identities, and use them to manufacture various attacks, such as advertising [8], [18], collecting personal privacy information [24], sending spam [7] and so on
MODEL OVERVIEW AND GRAPH MODEL In this work, we propose a scheme that use victim prediction to improve the accuracy of Sybil detection
Summary
Online Social Networks (OSNs) have emerged as important platforms for people to communicate across the globe. In order to create various attacks, Sybil will send a large number of friend requests to normal users. We propose a new victim prediction method to improve Sybil detection accuracy. As the victim accepted Sybil’s friend request, there are some connection edges between victims and Sybil accounts in the graph model. Chen: Efficient Victim Prediction for Sybil Detection in OSN edges are attack edges. We extracted features from the data set, and used the classifier to predict victims, which can effectively improve the accuracy of account sort, improving the efficiency of Sybil detection. A novel classifier for victim prediction is proposed, which can greatly improve the efficiency of Sybil detection.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
