基于知识图谱的恶意用户筛选算法研究

Research of Malicious Users Screening Algorithm Based on Knowledge Graph

如今互联网产业不断发展,诞生了面向广大用户的各类软件及网站,野蛮生长的同时安全需求也随之增加。除了常规的安全威胁以外,部分恶意用户的存在也是一个不容忽视的问题,恶意用户混杂在普通用户间进行操作增加了不必要甚至危险的数据流量,也影响了面向普通用户的各类学习算法的结果。而恶意用户间的外在联系以及恶意用户自身各项属性所带来的内在关联在提取后满足知识图谱构建的数据结构,且知识图谱可以根据实体间的关系进行知识推理,因此论文使用知识图谱相关算法来实现对于恶意用户的筛选,并通过仿真试验对使用知识图谱算法筛选恶意用户是否具有可行性进行了论证。

Nowadays,the internet industry continues to develop,and various software and websites with a lot of users have been born.The demand for security has also increased while the rapid growth has occurred.In addition to regular security threats,the existence of some malicious users is also a problem that cannot be ignored.The mixing of malicious users among ordinary users increases unnecessary or even dangerous data flow,and also affects the results of various learning algorithms for ordinary users.The external connections between malicious users and the internal associations brought by the various attributes of the malicious users satisfy the data structure constructed by the knowledge graph after processing,and the knowledge graph can perform knowledge reasoning based on the relationship between entities,so the knowledge graph algorithm is used to filter malicious users in this article.The simulation experiment in the third section of this article demonstrates whether it is feasible to use the knowledge graph algorithm to screen malicious users.