郑州大学学报（理学版）2026，Vol.58Issue(1)：27-34,8.DOI:10.13705/j.issn.1671-6841.2024126
基于改进GraphSAGE的网络攻击检测
Network Attack Detection Based on Improved GraphSAGE
摘要
Abstract
Network attack detection based on deep learning was modeled on Euclidean data and couldn′t capture the structural features within attack data.To address this issue,a network attack detection algo-rithm based on improved graph sample and aggregate(GraphSAGE)was proposed.Firstly,the attack data was initially transformed from a flat structure into a graph structure.Secondly,the GraphSAGE algo-rithm was enhanced in several ways,including the fusion of node and edge features during the message passing phase,consideration of the impact of different source nodes on the target node during the message aggregation phase,and the introduction of residual learning mechanism during the edge embedding gener-ation.The experimental results on two public network attack datasets showed that the overall performance of the proposed algorithm was superior to that of the E-GraphSAGE,LSTM,RNN,and CNN algorithms in binary classification scenarios.And the F1 values of the proposed algorithm were higher than compari-son algorithms on most attack categories in multi classification scenarios.关键词
网络攻击检测/深度学习/图神经网络/图采样与聚合/注意力机制Key words
network attack detection/deep learning/graph neural network/graph sample and aggre-gate/attention mechanism分类
信息技术与安全科学引用本文复制引用
闫彦彤,于文涛,李丽红,方伟..基于改进GraphSAGE的网络攻击检测[J].郑州大学学报（理学版）,2026,58(1):27-34,8.基金项目
河北省数据科学与应用重点实验室项目(10120201) （10120201）
唐山市数据科学重点实验室项目(10120301) （10120301）
