Mobile malicious user identification method and system based on communication behavior rule

Abstract

The invention relates to a mobile malicious user identification method and system based on a communication behavior rule, and the method comprises the steps: collecting data in desensitized mobile communication flow data based on a non-uniform sampling method, and carrying out preprocessing; analyzing and extracting call behavior characteristics, short message behavior characteristics and time distribution characteristics of the user by utilizing a behavior mode in a mobile communication behavior analysis model based on the preprocessed mobile communication sampling data; based on the preprocessed mobile communication sampling data, analyzing and extracting social attribute characteristics of the user by utilizing a communication network in a mobile communication behavior analysis model; and constructing a mobile malicious user identification model based on the extracted user behavior mode characteristics and the extracted user social attribute characteristics. The behavior rule of theuser can be analyzed based on the desensitization data, whether the user is a mobile malicious user or not is recognized, timeliness is achieved, and the mobile malicious user can be recognized withhigh accuracy under the condition that personal privacy of the user is not involved.

Description

technical field [0001] The invention relates to a mobile malicious user identification method and system based on communication behavior rules, and belongs to the technical field of network space security. Background technique [0002] At present, for different purposes and interests, more and more illegal organizations or individuals use mobile communication devices to carry out malicious acts on the mobile Internet, such as telecommunication fraud and spam messages. Personal life and property safety of mobile communication users and the stable development of society pose a great threat. The 2017 China Mobile Security Status Report released by 360 Internet Security Center shows that in 2017, 360 Mobile Guard intercepted 38.09 billion harassing phone numbers and 9.85 billion spam text messages for users across the country, timely and effectively identifying them. Mobile malicious users engaged in malicious behaviors such as telecommunication fraud have important research si...

AI Technical Summary

Problems solved by technology

[0008] The technology of the present invention solves the problem: In view of the hysteresis of the existing mobile malicious user identification solutions and the problem that the traditional social network abnormal user identification method cannot be directly used, a mobile malicious user identification method and system based on communication behavior rules are provided, which can be based on The desensitized data analyzes the user's behavior rules to identify whether the user is a mobile malicious user, which has good timeliness and can identify mobile malicious users with high accuracy without involving the user's personal privacy.

Images