摘要
在网络数据的采集与传输过程中,经常面临无法完全采集、信息丢失等情况。在不完全信息条件下的网络入侵检测成为网络异常检测的难题。为解决不完全信息入侵检测准确率的问题,结合网络数据的特点,文章提出一种基于不完全信息的深度学习网络入侵检测模型(NIDII-DL),借助多层感知神经网络构建深度学习模型,实现信息不完全条件下的入侵检测。实验结果表明,NIDII-DL方法在不完全信息条件下的分类精度高于其他算法,且对信息不完全的敏感度更低。
In the process of network data collection and transmission,the situation of incomplete collection and information loss occurs frequently. Network intrusion detection in the case of incomplete information has become a problem of network anomaly detection. Aiming at solving the problem of incomplete information intrusion detection accuracy,combined with the characteristics of network data,this paper proposes a deep learning network intrusion detection model (NIDLL-DL) based on incomplete information,which uses multi-layer perceptual neural network to construct deep learning model to realize intrusion detection under incomplete information. The experimental results show that the classification accuracy of NIDII-DL under incomplete information is higher than other algorithms,and its sensitivity to incomplete information is lower.
作者
饶绪黎
徐彭娜
陈志德
许力
RAO Xuli;XU Pengna;CHEN Zhide;XU Li(Laboratory of Network Security and Cryptography,Fujian Normal University,Fuzhou Fujian 350007,China;Department of Computer,Fuzhou Polytechnic,Fuzhou Fujian 350108,China)
出处
《信息网络安全》
CSCD
北大核心
2019年第6期53-60,共8页
Netinfo Security
基金
国家自然科学基金[61841701]
福建省教育厅科技项目[JAT160822]
关键词
不完全信息
网络入侵检测
多层感知
特征量
incomplete information
network intrusion detection
multi-layer perception
feature quantity
