Malicious social user detection method based on adversarial learning

Abstract

The invention discloses a malicious social user detection method based on adversarial learning. The malicious social user detection method mainly solves the problems that an existing malicious social user detection method is low in precision and poor in stability and reliability. According to the scheme, the method comprises the steps of 1) collecting data and establishing different databases; 2) constructing different feature maps according to the association between the user and the databases; 3) calculating different feature preferences according to the feature maps corresponding to the social data nodes of all published content of the user; 4) generating a training sample set and a test sample set; 5) constructing a neural network; 6) taking different feature preferences of the training samples as input, and training the neural network; and 7) inputting a test sample into the trained neural network to obtain a detection result. According to the method, the content feature preference, the attention feature preference and the propagation feature preference are comprehensively considered, the detection precision, stability and reliability are improved, and the method can be used for public opinion analysis, community discovery, false news detection and social network marketing.

Description

technical field [0001] The invention belongs to the technical field of network security, and further relates to a method for detecting malicious social users, which can be used for public opinion analysis, community discovery, false news detection, and social network marketing. Background technique [0002] Due to the openness of social networks and the abundance of user data information, there are a large number of malicious social users in social networks. Malicious social users perform various malicious activities and spread various malicious information, such as fake news, spreading advertisements, and phishing websites. Malicious social users interact with other normal social users by simulating the browsing traces of normal social users, such as false comments, sending malicious private messages, malicious mutual fans, malicious likes, malicious answers to questions, malicious addition of friends, in an attempt to interfere with public opinion and steal normal The per...

AI Technical Summary

Problems solved by technology

The neural network used in this method is an autoencoder model, and since it is susceptible to adversarial perturbations, even a small adversarial perturbation can cause the neural network to incorrectly predict the target with high confidence, resulting in low robustness of the neural network , thereby reducing the stability and reliability of malicious social user detection

Images