帮助 关于我们

返回检索结果

基于自编码网络特征降维的轻量级入侵检测模型
A Lightweight Intrusion Detection Model Based on Autoencoder Network with Feature Reduction

查看参考文献19篇

高妮 1   高岭 1   贺毅岳 2   王海 1  
文摘 基于支持向量机(SVM)的入侵检测方法受时间和空间复杂度约束,在高维特征空间计算时面临“维数灾害”的问题.为此,本文提出一种基于自编码网络的支持向量机入侵检测模型(AN-SVM).首先,该模型采用多层无监督的限制玻尔兹曼机(RBM)将高维、非线性的原始数据映射至低维空间,建立高维空间和低维空间的双向映射自编码网络结构,进而运用基于反向传播网络的自编码网络权值微调算法重构低维空间数据的最优高维表示,从而获得原始数据的相应最优低维表示;最后,采用SVM分类算法对所学习到的最优低维表示进行入侵识别.实验结果表明,AN-SVM模型降低了入侵检测模型中分类的训练时间和测试时间,并且分类效果优于传统算法,是一种可行且高效的轻量级入侵检测模型.
其他语种文摘 Owing to the constraints of time and space complexity, support vector machine (SVM) faced with the problem of ‘curse of dimensionality’when computation happens in high-dimensional feature space. Therefore, an intrusion detection model of support vector machine based on autoencoder network (AN-SVM) is proposed. First, the multilayer unsupervised restricted boltzmann machine (RBM) in our model is employed in mapping the vector of raw dada from high-dimensional nonlinear space to low-dimensional space, and a mutual mapping autoencoder network of high-dimensional space and low-dimensional space is constructed. Then autoencoder network weights of fine-tuning algorithm based on back propagation network is employed to reconstruct the new optimal high-dimensional representation of data in low-dimensional space, and the corresponding optimal low-dimensional representation of raw data can be obtained. Furthermore,SVM classification algorithm is employed to detect intrusion from the optimal low-dimensional data. The experimental results demonstrate that AN-SVM model can effectively reduce the training time and testing time of classifier in the intrusion detection model and its classification performance outperforms those traditional methods. So,AN-SVM model is a feasible and efficient lightweight intrusion detection model.
来源 电子学报 ,2017,45(3):730-739 【核心库】
DOI 10.3969/j.issn.0372-2112.2017.03.033
关键词 特征降维 ; 自编码网络 ; 限制玻尔兹曼机 ; 支持向量机 ; 入侵检测
地址

1. 西北大学信息科学与技术学院, 陕西, 西安, 710069  

2. 西北大学经济管理学院, 陕西, 西安, 710127

语种 中文
文献类型 研究性论文
ISSN 0372-2112
学科 自动化技术、计算机技术
基金 国家自然科学基金 ;  国家教育部人文社会科学研究青年项目 ;  陕西省自然科学基金
文献收藏号 CSCD:5981319

参考文献 共 19 共1页

1.  Wang G. A new approach to intrusion detection using artificial neural networks and fuzzy clustering. Expert Systems with Applications,2010,37(9):6225-6232 CSCD被引 13 次    
2.  Lin W C. CANN: An intrusion detection system based on combining cluster centers and nearest neighbors. Knowledge-Based Systems,2015,78:13-21 CSCD被引 14 次    
3.  Hoz E D L. Feature selection by multi-objective optimisation: Application to network anomaly detection by hierarchical self-organising maps. Knowledge-Based Systems,2014,71:322-338 CSCD被引 5 次    
4.  Vapnik V N. The nature of statistical learning theory. Neural Networks IEEE Transactions on,1995,10(5):988-999 CSCD被引 15 次    
5.  尚文利. 基于PSO-SVM的Modbus TCP通讯的异常检测方法. 电子学报,2014,11(42):2314-2320 CSCD被引 21 次    
6.  Chitrakar R. Selection of candidate support vectors in incremental SVM for network intrusion detection. Computers & Security,2014,45(3):231-241 CSCD被引 11 次    
7.  Kuang F. A novel approach of KPCA and SVM for intrusion detection. Journal of Computational Information Systems,2012,8(8):3237-3244 CSCD被引 3 次    
8.  Kuang F. A novel hybrid KPCA and SVM with GA model for intrusion detection. Applied Soft Computing,2014,18(4):178-184 CSCD被引 14 次    
9.  Ahmad I. Optimized intrusion detection mechanism using soft computing techniques. Telecommunication Systems,2013,52(4):2187-2195 CSCD被引 2 次    
10.  Lakhina S. Feature reduction using principal component analysis for effective anomaly-based intrusion detection on NSL - KDD. International Journal of Engineering Science & Technology,2010,2(6):1790-1799 CSCD被引 1 次    
11.  Hinton G E. Reducing the dimensionality of data with neural networks. Science,2006,313(28):504-507 CSCD被引 1753 次    
12.  Hinton G E. A fast learning algorithm for deep belief nets. Neural Computation,2006,18(7):1527-1554 CSCD被引 1400 次    
13.  余凯. 深度学习的昨天、今天和明天. 计算机研究与发展,2013,50(9):1799-1804 CSCD被引 202 次    
14.  Hinton G E. Training products of experts by minimizing contrastive divergence. Neural computation,2002,14(8):1771-1800 CSCD被引 276 次    
15.  Rumelhart D E. Learning representations by back-propagating errors. Nature,1986,323(6088):533-536 CSCD被引 1003 次    
16.  Stolfo S J. Cost-Based Modeling for Fraud and Intrusion Detection: Results from the JAM Project,2011 CSCD被引 2 次    
17.  Chang C C. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems & Technology,2011,2(3):389-396 CSCD被引 94 次    
18.  Larochelle H. Exploring strategies for training deep neural networks. Journal of Machine Learning Research,2009,10(6):1-40 CSCD被引 42 次    
19.  Williams N. A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. ACM SIGCOMM Computer Communication Review,2006,36(5):5-16 CSCD被引 33 次    
引证文献 24 篇

1 赵旭 基于改进选择算子的NIDS多媒体包多线程择危处理模型 信息网络安全,2018(10):45-50
CSCD被引 0 次

2 钱亚冠 一种针对基于SVM入侵检测系统的毒性攻击方法 电子学报,2019,47(1):59-65
CSCD被引 7 次

显示所有24篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号