Network fraud early warning method and device based on deceived group portrait

Abstract

The invention discloses a network fraud early warning method and device based on a deceived group portrait, and the method comprises the steps: obtaining a network fraud case fraud case sample, and extracting the information of a deceived person in a network fraud case; dividing the processed cheated person information into a test feature and a training feature; constructing an initial network fraud early warning model, training the initial network fraud early warning model according to the training feature, and verifying and evaluating the initial network fraud early warning model according to the test feature; when it is detected that the verification evaluation result meets a preset requirement, generating a target network fraud model; and obtaining personal information of the user, predicting whether the user is deceived or not according to the target network fraud model, and generating fraud early warning if the user is predicted to be deceived. According to the method, the targetnetwork fraud early warning model is generated by analyzing a large amount of deceived person information in the existing network fraud case, and the target network fraud early warning model performsearly warning on the deceived condition of a common user, so that financial loss of the user is effectively prevented.

Description

technical field [0001] The invention relates to the technical field of network security, in particular to a network fraud early warning method and device based on portraits of deceived groups. Background technique [0002] With the rapid development of computer networks and mobile communications, personal computers, smart phones and other mobile devices with Internet access have become indispensable tools in people's life and work, but the network security problems behind them are becoming more and more serious, and network fraud is one of them. At present, network fraud has become the main way of harming people's economic and property losses. There are many methods of online fraud. Fraudsters send content containing fraudulent information to victims through emails, text messages, phone calls, WeChat, etc., such as links containing Trojan horses, suspicious accounts, and even false information. The masses are deceived. [0003] The network fraud analysis method in the pri...

AI Technical Summary

Problems solved by technology

However, to determine whether suspicious information is Internet fraud information, one by one judgment is required, the workload is heavy, and the detection efficiency of Internet fraud in real life is low.

Images