《计算机应用研究》|Application Research of Computers

基于深度迁移学习的网络入侵检测

Network intrusion detection based on deep transfer learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 卢明星,杜国真,季泽旭
机构 1.河南护理职业学院 网络管理中心,河南 安阳 455000;2.中国科学技术大学 计算机科学与技术学院,合肥 230026
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)09-050-2811-04
DOI 10.19734/j.issn.1001-3695.2019.05.0147
摘要 为解决网络入侵检测问题,提高检测准确率和降低误报率,提出一种基于深度迁移学习的网络入侵检测方法,该方法使用非监督学习的深度自编码器来进行迁移学习,实现网络的入侵检测。首先对深度迁移学习问题进行建模,然后对深度模型进行迁移学习。迁移学习框架由嵌入层和标签层实现编/解码,编码和解码权重由源域和目标域共享,用于知识的迁移。嵌入层中,通过最小化域之间的嵌入实例的KL散度来强制源域和目标域数据的分布相似;在标签编码层中,使用softmax回归模型对源域的标签信息进行编码分类。实验结果表明,该方法能够实现网络入侵检测,且性能优于其他入侵检测方法。
关键词 深度自编码器; 迁移学习; 入侵检测; 嵌入层; 标签层
基金项目 2016年河南省教育厅高等学校青年骨干教师培养计划资助项目(2016GGJS-285)
本文URL http://www.arocmag.com/article/01-2020-09-050.html
英文标题 Network intrusion detection based on deep transfer learning
作者英文名 Lu Mingxing, Du Guozhen, Ji Zexu
机构英文名 1.Network Management Center,Henan Vocational College of Nursing,Anyang Henan 455000,China;2.School of Computer Science & Technology,University of Science & Technology of China,Hefei 230026,China
英文摘要 In order to solve the problem of network intrusion detection, improve detection accuracy and reduce false positive rate, this paper proposed a network intrusion detection method based on deep transfer learning. This method used unsupervised learning deep self-encoder for transfer learning to realize network intrusion detection. Firstly, it modeled the deep transfer learning problem, and then modeled the deep transfer learning problem. The transfer learning framework implemented encoding and decoding by embedding layer and label layer, and shared the weight of encoding and decoding by source domain and target domain for knowledge transferring. In the embedding layer, it compelled the distribution of source domain and target domain data to be similar by minimizing the KL divergence of embedded instances between domains. In the label coding layer, it coded and classified the label information of source domain by using the softwaremax regression model. The experimental results show that this method can implement network intrusion detection, and its performance is better than other intrusion detection methods.
英文关键词 deep self-encoder; migration learning; intrusion detection; embedded layer; label layer
参考文献 查看稿件参考文献
 
收稿日期 2019/5/7
修回日期 2019/6/25
页码 2811-2814
中图分类号 TP391
文献标志码 A