一种基于MetaCost和RF的网络入侵检测方法分析  

Analysis of a Network Intrusion Detection Method Based on MetaCost and Random Forest

作　　者：王雄伟 张鑫楠 WANG Xiongwei;ZHANG Xinnan(College of Artificial Intelligence,Caofeidian College of Technology,Hebei 063200,China)

机构地区：[1]曹妃甸职业技术学院人工智能学院,河北063200

出　　处：《电子技术（上海）》2024年第1期39-41,共3页Electronic Technology

摘　　要：阐述一种基于MetaCost-RF的网络入侵检测算法,该算法在RF训练过程中通过引入代价矩阵来减小不平衡数据集给RF带来的负面影响。在NSL-KDD上对训练好的模型进行测试验证,结果表明,MetaCost-RF对比RF在准确率上提高5.16个百分点,在三个少数类的召回率上分别提高了10.82、20.00和21.17个百分点,说明该模型有效提高了准确率和对少数类样本的召回率。This paper describes a network intrusion detection algorithm based on MetaCostRF by combining the cost-sensitive learning method.The algorithm reduces the negative impact of unbalanced datasets on RF by introducing a cost matrix during RF training.Test validation of trained models on NSL-KDD.The results show that the accuracy of MetaCost-RF is improved by 5.16percentage points compared with RF,and the recall rate of three minority classes is improved by 10.82,20.00 and 21.17 percentage points respectively.It is shown that the model is effective in enhancing the accuracy.Besides,it improving recall for a small number of classes of samples.

关 键 词：不平衡数据集 MetaCost 随机森林 网络入侵检测 代价矩阵 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]