【摘要】 针对传统机器学习方法在检测网络入侵时存在的问题,给出一种基于支持向量机(SVM)的网络入侵检测模型。大量实验证明:提出的网络入侵检测模型具有较高的检测率,避免了基于传统机器学习检测方法的局限性。在训练数据的过程中,考虑不同的网络数据特征对入侵检测结果的影响程度,还提出一种新的特征加权分类方法,并通过实验数据说明该方法可使检测精度有所提高。更多还原

【Abstract】 In view of the problems of using traditional machine learning method to detect the network intrusions,this paper proposes a network intrusion detection model based on support vector machine(SVM).Experimental results demonstrate that the proposed model has higher detection accuracy of intrusions and avoids the limitation of the detection methods based on traditional machine learning.In the training,considering the effect of different network data features on the intrusion detection results,a new weighted feature classification method is also brought forward,which improves the accuracy of network intrusion detection.更多还原