基于DNN-FM模型的网络入侵检测研究Research on network intrusion detection based on DNN-FM model
张全龙;王怀彬;
摘要(Abstract):
与随着网络技术的飞速发展,主动防御网络入侵比以往更加重要.误报率高和检测率低的主要原因之一是不能很好的对数据集间的特征进行交互学习.在本文中,我们提出了一种可以对低阶和高阶特征进行交互学习的模型.模型DNN-FM在新的神经网络体系结构中结合了因子分解机和深度神经网络对低阶和高阶特征进行交互学习.在KDD99数据集上进行了实验之后,证明DNN-FM模型与现有网络入侵检测模型相比,有更高的检测率.
关键词(KeyWords): 网络入侵检测;深度神经网络;因子分解机;DNN-FM;特征交互
基金项目(Foundation): 天津科技重大专项(16YDLJGX00210)
作者(Author): 张全龙;王怀彬;
Email:
DOI:
参考文献(References):
- [1]Anderson J P.Computer security threat monitoring and surveillance[J].Technical Report,James P.Anderson Company,1980,2(6):1-3.
- [2]Mukkamala S,Janoski G,Sung A.Intrusion detection using neural networks and support vector machines[C]//International Joint Conference on Neural Networks.New Mexico,USA:IEEE,2002:38-45.
- [3]Hu W,Hu W.Network-based intrusion detection using Adaboost algorithm[C]//The 2005 IEEE/WIC/ACM International Conference on Web Intelligence.Washington,US-A:ACM,2005:171-175.
- [4]Ajagekar S K,Jadhav V.Automated Approach for DDOSattacks detection based on naive bayes multinomial classifier[C]//2018 2nd International Conference on Trends in Electronics and Informatics(ICOEI).Tirunelveli,India:IEEE,2018:1-5.
- [5]Li W,Li Q X.Using naive bayes with ada Boost to enhance network anomaly intrusion detection[M].Shenyang,China:IEEE,2010:10-15.
- [6]Xiaofeng Z,Xiaohong H.Research on intrusion detection based on improved combination of K-means and multi-level SVM[C]//2017 IEEE 17th International Conference on Communication Technology (ICCT).Chengdu,China:IEEE,2017:2042-2045.
- [7]Hao X,Zhang X.Research on abnormal detection based on improved combination of k-means and SVDD[J].IOP Conference Series Earth and Environmental Science,2018,114:30-35.
- [8]Aung Y Y,Min M M.Hybrid intrusion detection system using K-means and K-nearest neighbor algorithms[C]//2018IEEE/ACIS 17th International Conference on Computer and Information Science(ICIS).Singapore:IEEE,2018:34-38.
- [9]Liu W,Wang Z,Liu X,et al.A survey of deep neural network architectures and their applications[J].Neurocomputing,2017,234:11-26.
- [10]Kunhare N,Tiwari R.Study of the attributes using four class labels on KDD99 and NSL-KDD datasets with machine learning techniques[C]//2018 8th International Conference on Communication Systems and Network Technologies (CSNT).Gwalior,India:IEEE,2018:127-131.
- [11]Chao D,Gang Z,Yu-Jiao L,et al.The detection of network intrusion based on improved adaboost algorithm[J].Journal of Sichuan University(Natural Science Edition),2015,5(3):2-6.
- [12]Feng W,Zhang Q,Hu G,et al.Mining network data for intrusion detection through combining SVMs with ant colony networks[J].Future Generation Computer Systems,2014,37:127-140.
- [13]Chun-Lin L I,Huang Y J,Wang H,et al.Detection of network intrusion based on deep learning[J].Information security&communications privacy,2014,10:68-72.
- [14]Leksin V,Ostapets A.Job recommendation based on factorization machine and topic modelling[C]//Proceedings of the Recommender Systems Challenge.New York:ACM,2016:6.