【摘要】 在网络安全问题的研究中,传统检测模型对网络攻击的检测率较低。为了进一步提高网络安全,利用集成特征选择算法进行重要特征提取;构建多分类器模型,并在NUSW-NB15数据集上做实验验证。实验结果表明,所提出的基于集成特征选择的入侵检测模型能很好的识别攻击类型数据,在整体的准确率和G平均指标上统计值达到97.09%、89.10%,能有效识别网络流量中的异常攻击。更多还原

【Abstract】 In the research of network security, the traditional detection model has low detection rate of attacks. In order to further improve network security, an intrusion detection model based on integrated feature selection is proposed. Firstly, the integrated feature selection algorithm is used to extract the important features of the data set. Then, a multi-classifier model was constructed and tested experimentally on the NUSW-NB15 data set. Experimental results show that the intrusion detection model proposed in this paper can identify attack type data,and the statistical values of the overall accuracy and G-mean index have reached 97.09% and 89.10%, which can effectively identify abnormal at-tacks in network traffic.更多还原