基于在线学习RBFNN的网络安全态势预测技术研究

doi:10.3969/j.issn.1671-1122.2016.04.004

摘要/Abstract

摘要：

随着网络攻击事件愈演愈烈,现有的网络防御技术已经不能满足当今形势下大规模网络安全的需求,网络安全态势预测作为一项新的网络安全主动防御技术应运而生。当前,将人工神经网络并行化处理非线性数据的能力用于网络安全态势预测已成为主流。在使用人工神经网络建模并进行网络安全态势预测时,多数采用的是离线学习算法,需要提前设计好网络结构及参数。但是,如果输入样本维数发生变化,必须重新设计模型结构和训练网络参数,否则,会造成预测结果误差过大,达不到预期效果。这无疑增加了操作复杂度,浪费大量的时间,不符合网络安全态势预测实时性的特点。针对以上问题,文章结合在线学习RBFNN自适应动态调整网络结构的特点,提出分组优化法训练网络参数,建立基于在线学习RBFNN的网络安全态势预测模型,并对网络安全态势进行预测。

关键词: 网络安全态势预测, 在线学习, RBFNN

Abstract:

With the network attacks increasing rapaidly, the traditional network security technologies unable to meet the demand of network security. As a new and active network security defense technology, network security situation prediction comes forth. In the majority of cases the network security situation prediction technique based on artificial neural network adopt outline learning. It demanded design network structure and parameter ahead of schedule. If input stylebook dimension begins to change, the network structure and parameter must be designed again. This will undoubtedly increase the complexity of the operation and waste a lot of time. This paper researches the method of adaptive dynamic adjustment network structure of the online learning RBFNN. A group training method is put forward to train the network. This paper proposes a new method of network security situation prediction model based on online learning RBFNN.

Key words: network security situation prediction, online learning, RBFNN

中图分类号:

TP309

薛丽敏, 李忠, 蓝湾湾. 基于在线学习RBFNN的网络安全态势预测技术研究[J]. 信息网络安全, 2016, 16(4): 23-30.

Limin XUE, Zhong LI, Wanwan LAN. Research on Network Security Situation Prediction Technique Based on Online Learning RBFNN[J]. Netinfo Security, 2016, 16(4): 23-30.

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

图8

参考文献 31

[1]	NANDA S, DEO N.A Highly Scalable Model for Network Attack Identification and Path Prediction[C]//IEEE. IEEE SoutheastCon 2007, March 22-25, 2007, Riehmond, VA. New Jersey: IEEE, 2007: 663-668.
[2]	PALETTA M, HERRERO P.Foreseeing Cooperation Behaviors in Collaborative Grid Environments[C]//Springer. 7th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS 2009), March 25-27, 2009, Spain. Heidelberg: Springer, 2009: 120-129.
[3]	LI Juan, LI Tao, LIANG Gang.A Network Security Dynamic Situation Forecasting Method[C]//IEEE. 2009 International Forum on Information Technology and Applications, May 15-17, 2009, Chengdu, China. New Jersey: IEEE, 2009: 115-118.
[4]	MAN Dapeng, WANG Yan, YANG Wu, et al.A Combined Prediction Method for Network Security Situation[C]//IEEE. 2010 International Conference on Computational Intelligence and Software Engineering (CiSE), December 10-12, 2010, Wuhan, China. New Jersey: IEEE, 2010: 1-4.
[5]	吴拥民,李冬银. 基于IPSO和BPNN的网络安全态势预测[J]. 岷江学院学报,2013,34(5):78-83.
[6]	曾斌,钟萍. 网络安全态势预测方法的仿真研究[J]. 计算机仿真,2012,29(5):170-173.
[7]	孟锦,马驰,何加浪,等. 基于HHGA-RBF神经网络的网络安全态势预测模型[J]. 计算机科学,2011,38(7):70-75.
[8]	李凯,曹阳. 基于ARIMA模型的网络安全威胁态势预测方法[J]. 计算机应用研究,2012,29(8):3042-3045.
[9]	陈善学,杨政,朱江,等. 一种基于累加PSO-SVM的网络安全态势预测模型[J]. 计算机应用研究,2014,32(6):135-139.
[10]	张安楠,苏旸. 基于小波变换的网络安全态势复合预测方法[J]. 计算机仿真,2014,31(6):282-286.
[11]	HUANG Guangbin, CHEN Lei, SIEW C K.Universal Approximation Using Incremental Constructive Feedforward Networks with Random Hidden Nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892.
[12]	LAURET P, FOCK E, MARA T A.A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method[J]. IEEE Transactions on Neural Networks, 2006, 17(2): 273-293.
[13]	张米娜,韩红桂,乔俊飞. 前馈神经网络结构动态增长—修剪方法[J]. 智能系统学报,2011,6(2):101-106.
[14]	张昭昭,乔俊飞,杨刚. 自适应前馈神经网络结构优化设计[J]. 智能系统学报,2011,6(4):312-317.
[15]	张伟,乔俊飞,李凡军. 溶解氧浓度的直接自适应动态神经网络控制方法[J]. 控制理论与应用,2015,32(1):115-121.
[16]	ISLAM M M, SATTAR M A, AMIN M F, et al.A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2009, 39(3): 705-722.
[17]	BAO Jian, CHEN Yu, YU Jinshou.A Regeneratable Dynamaic Differential Evolution Algorithm for Neural Networks with Integer Weights[J]. Journal of Zhejiang University SICENCE C (Computers & Electornics), 2010, 11(12): 939-947.
[18]	DING Shifei, SU Chunyang, YU Junzhao.An Optimizing BP Neural Network Algorithm Based on Genetic Algorithm[J]. Artificial Intelligence Review, 2011, 36(2): 153-162.
[19]	涂涓涓. PSO优化神经网络算法的研究及其应用[D]. 镇江:江苏大学,2013.
[20]	张小鸣,王研顺. 改进型RBF神经网络在线的学习算法[J]. 常州大学学报(自然科学版),2014,26(6):52-56.
[21]	YIN H, ALLINSON N M.Self-organizing Mixture Networks for Probability Density Estimation[J]. IEEE Transactions on Neural Networks, 2001, 12(2): 405-411.
[22]	BORS A G, PITAS I.Median Radial Basis Function Neural Network[J]. IEEE Transactions on Neural Networks, 1996, 7(6): 1351-1364.
[23]	王景中,徐友强. 基于RBF神经网络的HTTP异常行为自动识别方法[J]. 信息网络安全,2014(12):16-20.
[24]	乔俊飞,韩红桂. 神经网络结构动态优化设计的分析与展望[J]. 控制理论与应用,2010,27(3):350-357.
[25]	黄红梅,胡寿松. 基于在线学习RBF神经网络的故障预报[J]. 南京航空航天大学学报,2007,39(2):249-252.
[26]	CANO-IZQUIERDO J M, IBARROLA J, PINZOLAS M, et al. DNSP: A Biologically Inspired Dynamic Neural Network Approach to Signal Processing[J]. Neural Networks, 2008, 21(7): 1006-1019.
[27]	CHENG W S. Automatic Control Theory, Method and Application[M]. Beijing: Tsinghua University Press, 2009.
[28]	姚洪磊,张彦. 基于BP神经网络的铁路互联网售票系统信息安全评估方法[J]. 信息网络安全,2014(7):81-86.
[29]	蓝湾湾,薛丽敏. 基于改进粒子群小波神经网络的网络安全态势预测模型[J]. 大连舰艇学院学报,2015,38(5):72-76.
[30]	任伟,蒋兴浩,孙锬锋. 基于RBF神经网络的网络安全态势预测方法[J]. 计算机工程与应用,2006,31(40):136-138.
[31]	伍海波. 基于神经网络的检测器生成算法研究与应用[J]. 信息网络安全,2015(9):249-252.