正在加载图片...
第8卷第6期 智能系统学报 Vol.8 No.6 2013年12月 CAAI Transactions on Intelligent Systems Dec.2013 D0:10.3969/j.issn.1673-4785.201304040 网络出版地址:http://www.enki..net/kcms/detail/23.1538.TP.20130603.1601.005.html 变异粒子群优化的BP神经网络 在入侵检测中的应用 宋玲,常磊 (1.广西大学计算机与电子信息学院,广西南宁530004:2.河北化工医药职业技术学院信息工程系,河北石家庄050026) 摘要:针对人侵检测系统的自主学习性、实时性,提出带变异算子的粒子群优化方法,并用该方法优化BP神经网 络以加快其收敛速度,提出了MPSO_BP混合优化算法.为提高入侵检测系统的检测率、降低误报率,提出了一种新 的入侵检测模型(MPBIDS).采取is数据集对3个BP神经网络进行模拟实验,结果表明,优化后的BP神经网络具 有更好的收敛速度和精度.将改进的BP神经网络应用到入侵检测中,采取KDDCUP99为测试数据集,仿真结果表 明,基于改进BP神经网络的入侵检测模型能提高检测率、降低误报率 关键词:变异算子;入侵检测系统:粒子群优化算法:BP神经网络 中图分类号:TP393文献标志码:A文章编号:1673-4785(2013)06-0558-06 中文引用格式:宋龄,常磊.变异粒子群优化的BP神经网络在入侵检测中的应用[J].智能系统学报,2013,8(6):558-563. 英文引用格式:SONG Ling,CHANG Lei.Application of mutation particle swarm optimization based BP neural network in the in trusion detection system[J].CAAI Transactions on Intelligent Systems,2013,8(6):558-563. Application of mutation particle swarm optimization based BP neural network in the intrusion detection system SONG Ling',CHANG Lei2 (1.School of Computer,Electronics and Information,Guangxi University,Nanning 530004,China;2.Department of Information En- gineering,Hebei Chemical and Pharmaceutical College,Shijiazhuang 050026,China) Abstract:A aiming at the properties of real-time performance and self-learning of the intrusion detection system (IDS),an improved particle swarm optimization (PSO)based on the mutation operator was proposed,which was used to optimize BP neural network,so as to accelerate convergence speed of BP neural network,thus,the MPSO _BP hybrid optimization algorithm is presented.In order to increase detection rate and lower false alarm rate of the intrusion detection system,a new intrusion detection model(MPBIDS)was put forward.Iris data set was applied to the three BP neural networks for simulation.Experiment results show that the optimized BP neural network had bet- ter convergence speed and accuracy.Based on this finding,the improved BP network was applied to intrusion de- tection,taking KDDCUP99 as the test data set.The simulation result proves that the IDS with improved BP network can improve the detection rate and reduce the false alarm rate. Keywords:mutation operator;intrusion detection system;particle swarm optimization;BP neural network 随着网络技术的飞速发展,网络安全问题日益 步显现其缺点和不足[山. 重要,如何保护网络免受攻击越来越迫在眉睫.网络 近年来,反向传播(back-propagation,.BP)神经 入侵检测是网络安全技术的重要组成部分,也是当 网络被广泛应用于许多领域,并取得了良好的效果。 前研究的热点之一.但是,传统的入侵检测技术正逐 然而,在实际应用中,BP网络也暴露出一些固有的 缺陷,最明显的是收敛速度慢.与传统的BP算法相 收稿日期:2013-04-15.网络出版日期:2013-06-03 基金项目:国家自然科学基金资助项目(60963022). 比,可以用遗传算法、蚁群算法和PSO(particle 通信作者:宋玲.E-mail:aling7197_cn@sina.com swarm optimization)算法等来优化BP神经网络,如第 8 卷第 6 期 智 能 系 统 学 报 Vol.8 №.6 2013 年 12 月 CAAI Transactions on Intelligent Systems Dec. 2013 DOI:10.3969 / j.issn.1673⁃4785.201304040 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20130603.1601.005.html 变异粒子群优化的 BP 神经网络 在入侵检测中的应用 宋玲1 ,常磊2 (1. 广西大学 计算机与电子信息学院,广西 南宁 530004; 2. 河北化工医药职业技术学院 信息工程系,河北 石家庄 050026) 摘 要:针对入侵检测系统的自主学习性、实时性,提出带变异算子的粒子群优化方法,并用该方法优化 BP 神经网 络以加快其收敛速度,提出了 MPSO_BP 混合优化算法.为提高入侵检测系统的检测率、降低误报率,提出了一种新 的入侵检测模型(MPBIDS).采取 Iris 数据集对 3 个 BP 神经网络进行模拟实验,结果表明,优化后的 BP 神经网络具 有更好的收敛速度和精度.将改进的 BP 神经网络应用到入侵检测中,采取 KDDCUP99 为测试数据集,仿真结果表 明,基于改进 BP 神经网络的入侵检测模型能提高检测率、降低误报率. 关键词:变异算子;入侵检测系统;粒子群优化算法;BP 神经网络 中图分类号:TP393 文献标志码:A 文章编号:1673⁃4785(2013)06⁃0558⁃06 中文引用格式:宋龄,常磊. 变异粒子群优化的 BP 神经网络在入侵检测中的应用[J]. 智能系统学报, 2013, 8(6): 558⁃563. 英文引用格式:SONG Ling, CHANG Lei. Application of mutation particle swarm optimization based BP neural network in the in⁃ trusion detection system[J]. CAAI Transactions on Intelligent Systems, 2013, 8(6): 558⁃563. Application of mutation particle swarm optimization based BP neural network in the intrusion detection system SONG Ling 1 , CHANG Lei 2 (1. School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China; 2. Department of Information En⁃ gineering, Hebei Chemical and Pharmaceutical College, Shijiazhuang 050026, China) Abstract:A aiming at the properties of real⁃time performance and self⁃learning of the intrusion detection system (IDS), an improved particle swarm optimization (PSO) based on the mutation operator was proposed, which was used to optimize BP neural network, so as to accelerate convergence speed of BP neural network, thus, the MPSO _BP hybrid optimization algorithm is presented. In order to increase detection rate and lower false alarm rate of the intrusion detection system, a new intrusion detection model (MPBIDS) was put forward. Iris data set was applied to the three BP neural networks for simulation. Experiment results show that the optimized BP neural network had bet⁃ ter convergence speed and accuracy. Based on this finding, the improved BP network was applied to intrusion de⁃ tection, taking KDDCUP99 as the test data set. The simulation result proves that the IDS with improved BP network can improve the detection rate and reduce the false alarm rate. Keywords:mutation operator; intrusion detection system; particle swarm optimization; BP neural network 收稿日期:2013⁃04⁃15. 网络出版日期:2013⁃06⁃03. 基金项目:国家自然科学基金资助项目(60963022). 通信作者:宋玲. E⁃mail:aling7197_cn@ sina.com. 随着网络技术的飞速发展,网络安全问题日益 重要,如何保护网络免受攻击越来越迫在眉睫.网络 入侵检测是网络安全技术的重要组成部分,也是当 前研究的热点之一.但是,传统的入侵检测技术正逐 步显现其缺点和不足[1] . 近年来,反向传播( back⁃propagation, BP) 神经 网络被广泛应用于许多领域,并取得了良好的效果. 然而,在实际应用中,BP 网络也暴露出一些固有的 缺陷,最明显的是收敛速度慢.与传统的 BP 算法相 比,可 以 用 遗 传 算 法、 蚁 群 算 法 和 PSO ( particle swarm optimization) 算法等来优化 BP 神经网络,如
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有