Spam detection device and method based on user relationship mining and credit evaluation

Abstract

The invention provides a spam detection device and a method based on user relationship mining and credit evaluation. The detection device comprises a user relationship modeling device, a fingerprint collecting device, a path mining device, an email evaluating device, an email outputting device, a user evaluating device and a credit updating device. The method comprises the following steps: establishing a user relationship model according to the user communication relationship in a controlled network, then mining a specific path set according to the user relationship model, and finally establishing email determination records through the historical evaluation of the user on the path set and identifying email attributes. The device has the advantages that the device has good identification ability and can well identify malicious users and resist the interferences of the malicious users, can be deployed at entrances and exits of an email server, a gateway and a backbone network and be widely applied in the email filtering technology and other application fields.

Description

(1) Technical field [0001] The invention relates to the technical field of e-mail processing, in particular to a junk mail filtering technology. (2) Background technology [0002] E-mail has brought great convenience to people's work and life since its creation, but the problem of spam has become more and more serious. Spam not only occupies a large amount of network resources, but also seriously endangers people's interests. How to quickly, efficiently and accurately identify spam has also become the focus of scholars' research. [0003] At present, spam detection technology mainly includes detection technology based on mail content and detection technology based on mail behavior. Content-based detection technology identifies spam by finding the similarity of spam in content features, such as Bayesian filtering method. This technology consumes a lot of system resources in the process of training, classification, and calculation, and the processing efficiency is very low....

AI Technical Summary

Problems solved by technology

The downside is that malicious users can gain a high reputation with a large number of correct reviews and then send spam

Since the connection between users is not considered, this system is not ideal for environments with a large number of malicious users (Trusting spam reporters: A reporter-based reputation system for email filtering, ACM Transactions on Information Systems (TOIS), v. 27n.1, p.1-27, December 2008)

[0007] The above detection methods either detect the nature of spam from the characteristics of the mail itself, or detect the nature of spam based on the user's evaluation of the mail, but do not take into account the relationship between mail recipients

Images