基于XGBoost算法的内部网络安全威胁检测方法
Threat Detection Method of Internal Network Security Based on XGBoost Algorithm
丁梓轩 1陈国1
作者信息
- 1. 南京医科大学附属儿童医院信息科,南京 210008
- 折叠
摘要
针对内部网络安全威胁节点成因多、特征难捕捉问题,提出一种基于XGBoost算法的内部网络安全威胁检测方法.以内部网络社区间的状态差异作为指标,计算不同社区类型内节点的边权重,查找与目标值存在关联性的节点.经多次分配提取特征值,将其作为初始值输入XGBoost决策树中,构建威胁性特征目标函数,求解每个节点对应的泰勒系数,实现内部网络安全威胁检测.实验结果表明,所提方法特征提取精准度高,在多种网络攻击条件下均能实现精准检测.
Abstract
Aiming at the many causes and difficult features of internal network security threat nodes,an internal network security threat detection method based on XGBoost algorithm is proposed.Using the state differences between the internal network communities as an indicator,the edge weights of the nodes within different community types are calculated to find the nodes associated with the target values.Eigenvalues extracted through multiple assignments are taken as the initial input value XGBoost decision tree to construct the threat feature objective function,solve the corresponding Taylor coefficient of each node,and realize internal network security threat detection.The experimental data show that the proposed method has high feature extraction accuracy and can achieve accurate detection under various network attack conditions.
关键词
XGBoost算法/安全威胁检测/目标函数/泰勒系数/网络社区Key words
XGBoost algorithm/security threat detection/objective function/taylor coefficient/network community引用本文复制引用
基金项目
江苏省妇幼保健协会科研项目(FYX202201)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据