Fraud information filtering system and method on basis of feature identification

Abstract

The invention discloses a fraud information filtering system on the basis of the feature identification, which comprises a client and a server which are connected by a network. The client comprises a feature identification subsystem, a classification filtering subsystem and an information interception center; the feature identification subsystem is arranged in front of the classification filtering subsystem and is used for identifying fraud information; the classification filtering subsystem is used for identifying junk information; the information interception center is used for intercepting the fraud information and the junk information which are identified by the two subsystems; and the server is provided with a safety service cloud center and is used for monitoring the process of the client and carrying out data synchronism with the client by the network. The invention also discloses a fraud information filtering method on the basis of the system. According to the fraud information filtering system and the fraud information method, by feature detection, the fraud information with larger hazard is firstly filtered out before the junk information is filtered; and by the process linkage of the client and the server, a user is further prevented from accessing a malicious website, so that the probability that the fund account of the user is stolen is reduced.

Description

technical field [0001] The invention relates to the field of information security, in particular to a fraud information filtering system and method based on feature recognition. Background technique [0002] With the popularization of online banking, fraudulent text messages and emails of online banking are becoming more and more rampant. Usually, such fraudulent text messages or emails contain links to phishing websites. Induced to visit the phishing website, and enter their own online banking account number and password and other information on the phishing website, resulting in the theft of the user's bank account and causing direct economic losses to the user. [0003] The existing SMS spam filtering system mainly judges and prompts spam messages to users through classification algorithms such as Bayesian and Support Vector Machine (SVM). Bayesian classification is an algorithm that uses probability and statistical knowledge for classification, while support vector mach...

AI Technical Summary

Problems solved by technology

[0004] The spam message filtering system described above is also relatively simple to deal with after judging spam messages. It just marks text messages or emails as spam messages, and does not distinguish between online banking fraud messages that are more harmful and general advertising spam messages, let alone combine them. The detected spam information is processed in conjunction with anti-phishing, so it is impossible to prevent users from being phished

Images