Sybil attack detection method based on node attention and forwarding characteristics and electronic equipment

Abstract

The invention discloses a Sybil attack detection method and electronic equipment based on node attention and forwarding characteristics, and the detection method comprises the steps: obtaining social network user behavior data, and extracting a node feature vector and a node pair feature vector from the social network user behavior data based on the node attention and forwarding characteristics; inputting the node feature vector into a preset node classifier to obtain an initial trust value of the node, and inputting the node pair feature vector into a preset node pair classifier to obtain an initial trust value of the node pair; constructing a weighted strong social graph according to a preset social graph and the initial trust values of the node pairs; and carrying out trust propagation in the weighted strong social graph according to the initial trust values of the nodes by using a random walk algorithm to obtain a Sybil node set and a benign node set. According to the method, the user behavior information is integrated in the graph structure of the social network, so that the Sybil detection accuracy and practicability are effectively improved, and the method is simple and easy to implement.

Description

technical field [0001] The invention relates to the technical field of computer and information security, in particular to a Sybil attack detection method and electronic equipment based on node attention and forwarding features. Background technique [0002] Sybil attack refers to an attack method in which attackers use a large number of false identities created by them (that is, Sybil identities) to carry out malicious activities and destroy system functions. At present, the mainstream detection methods of Sybil attacks in social networks are divided into two categories, namely detection methods based on graph structure and detection methods based on node characteristics. [0003] However, the above mainstream Sybil attack detection methods all have certain limitations. Among them, the detection method based on the graph structure relies too much on the structural assumption, which does not hold true in the real social network, thus greatly reducing the effectiveness of th...

AI Technical Summary

Problems solved by technology

For this reason, the first object of the present invention is to propose a Sybil attack detection method based on node attention and forwarding characteristics, by utilizing the characteristics of user behavior characteristics and user tags being correlated, an initial trust value is generated based on user behavior characteristics, and in Based on the social graph, the initial trust value is added to construct a weighted strong social graph to detect Sybil nodes according to the weighted strong social graph, thus solving the limitations of the initial trust value setting of the detection method based on the graph structure and the detection method based on node characteristics The problem of poor feature robustness improves the accuracy of Sybil detection

Images