单小撤,
昆明理工大学信息工程与自动化学院 昆明 650500
详细信息
作者简介:缪祥华：男，1972年，博士后，副教授，研究方向为信息安全、网络安全、移动通信安全
单小撤：男，1992年，硕士生，研究方向为信息安全、入侵检测
通讯作者:单小撤 2258868766@qq.com
中图分类号:TN918.91计量
文章访问数:2262
HTML全文浏览量:606
PDF下载量:97
被引次数:0
出版历程
收稿日期:2019-08-29
修回日期:2020-05-09
网络出版日期:2020-05-28
刊出日期:2020-11-16
Research on Intrusion Detection Technology Based on Densely Connected Convolutional Neural Networks
Xianghua MIAO,Xiaoche SHAN,
School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
摘要
摘要:卷积神经网络在入侵检测技术领域中已得到广泛应用，一般地认为层次越深的网络结构其在特征提取、检测准确率等方面就越精确。但也伴随着梯度弥散、泛化能力不足且参数量大准确率不高等问题。针对上述问题，该文提出将密集连接卷积神经网络(DCCNet)应用到入侵检测技术中，并通过使用混合损失函数达到提升检测准确率的目的。用KDD 99数据集进行实验，将实验结果与常用的LeNet神经网络、VggNet神经网络结构相比。分析显示在检测的准确率上有一定的提高，而且缓解了在训练过程中梯度弥散问题。
关键词:入侵检测/
卷积神经网络/
密集连接/
梯度弥散
Abstract:Convolutional Neural Network (CNN) is widely used in the field of intrusion detection technology. It is generally believed that the deeper the network structure, the more accurate in feature extraction and detection accuracy. However, it is accompanied with the problems of gradient dispersion, insufficient generalization ability and low accuracy of parameters. In view of the above problems, the Densely Connected Convolutional Network (DCCNet) is applied into the intrusion detection technology, and achieve the purpose of improving the detection accuracy by using the hybrid loss function. Experiments are performed with the KDD 99 data set, and the experimental results are compared with the commonly used LeNet neural network and VggNet neural network structure. Finally, the analysis shows that the accuracy of detection is improved, and the problem of gradient vanishing during training is alleviated.
Key words:Intrusion detection/
Convolutional Neural Network (CNN)/
Dense connection/
Gradient vanishing
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=1293a7dd-dfbc-4a7c-99ce-11d1be156c9e
