基于蝙蝠优化算法的网络入侵检测模型

Network Intrusion Detection Model Based on Bat Optimization Algorithm

摘要: 网络入侵具有突发性和隐蔽性等特点，传统的技术很难描述其变化规律，这导致入侵检测正确率非常的低。为了提高入侵检测正确率，降低误检率，提出了一种基于动态自适应权重和柯西变异的蝙蝠优化算法优化神经网络的入侵检测模型。需要先采集入侵网络的数据进行整理，然后导入到神经网络中学习，采用蝙蝠优化算法优化网络模型的参数。最后选取KDD CUP 99数据集进行网络入侵检测的仿真实验。结果表明，本文模型能够获得理想的网络入侵检测率和误检率。

Abstract: Network intrusion has the characteristics of sudden and concealment, and the traditional technology is difficult to describe the law of change, which leads to a very low accuracy of intrusion detection. In order to improve the accuracy of intrusion detection and reduce the false detection rate, a bat optimization algorithm based on dynamic adaptive weight and Cauchy mutation was proposed to optimize the neural network intrusion detection model. It is necessary to collect the data of the intrusion network and then import the data into the neural network to learn. The bat optimization algorithm is used to optimize the parameters of the network model. Finally, the KDD CUP 99 dataset is selected to simulate the network intrusion detection. The results show that the proposed model can obtain ideal network intrusion detection rate and false detection rate.

文章引用：赵青杰, 王龙葛, 李捷, 于俊洋. 基于蝙蝠优化算法的网络入侵检测模型[J]. 计算机科学与应用, 2018, 8(11): 1650-1656. https://doi.org/10.12677/CSA.2018.811181

参考文献

[1]	高阳. 机器学习在网络入侵检测中的应用浅谈[J]. 电脑迷, 2018(9): 178.
[2]	颜谦和, 颜珍平. 遗传算法优化的神经网络入侵检测系统[J]. 计算机仿真, 2011, 28(4): 141-144.
[3]	陈仕涛, 陈国龙, 郭文忠, 等. 基于粒子群优化和邻域约简的入侵检测日志数据特征选择[J]. 计算机研究与发展, 2010, 47(7): 1261-1267.
[4]	Hong, S.-J., et al. (2011) A Novel Intrusion Detection System Based on Hierarchical Clustering and Support Vector Machines. Expert Systems with Appli-cations, 38, 306-313. [Google Scholar] [CrossRef]
[5]	顾丽, 王广泽, 乔佩利. 基于改进遗传算法的入侵检测的研究[J]. 信息技术, 2009, 33(7): 58-61, 65.
[6]	杨富华, 彭刚. PCA-SVM在网络入侵检测中的仿真研究[J]. 计算机仿真, 2011, 28(7): 146-149.
[7]	Wang, X.S. (2010) A New Metaheuristic Bat-Inspired Algorithm. Nature Inspired Cooperative Strategies for Optimization, Studies in Computational Intelligence, Springer-Verlag, Berlin Heidelberg, 10: 65-74.
[8]	Yang, X.S. (2011) Bat Algorithm for Multi-Objective Optimization. International Journal of Bio-Inspired Com-putation (IJBIC), 3, 267-274. [Google Scholar] [CrossRef]
[9]	Yang, X.S. and Gandomi, A.H. (2012) Bat Algorithm: A Novel Approach for Global Engineering Optimization. Engineering Computation, 29, 267-289. [Google Scholar] [CrossRef]
[10]	刘羿. 蝙蝠算法优化神经网络的网络入侵检测[J]. 计算机仿真, 2015, 32(2): 311-314.
[11]	Denning, D.E. (2010) An Intrusion Detection Model. IEEE Transaction on Software Engineering, 13, 222-232. [Google Scholar] [CrossRef]
[12]	李小剑, 谢晓尧. 基于支持向量机与k近邻相结合的网络入侵检测研究[J]. 贵州师范大学学报(自然科学版), 2015, 33(3): 86-91.
[13]	王云鹏, 张浩. 基于支持向量机的网络入侵检测算法综述[J]. 科学技术创新, 2017(25): 136-137.
[14]	谢康. 基于神经网络的入侵检测相关技术研究[D]: [博士学位论文]. 济南: 山东大学信息科学与工程学院, 2016.
[15]	Scardapane, S. and Uncini, A. (2017) Semi-Supervised Echo State Networks for Audio Classi-fication. Cognitive Computation, 9, 125-135. [Google Scholar] [CrossRef]
[16]	丁少华. 人工鱼算法优化神经网络的网络入侵检测[J]. 中国信息技术教育, 2014(20): 61.
[17]	贾会群, 魏仲慧, 何昕, 李沐雨. 基于神经网络与最小二乘法的车道线检测算法研究[J]. 汽车工程, 2018, 40(3): 363-368.
[18]	郭振洲, 王平, 马云峰, 王琦, 拱长青. 基于自适应权重和柯西变异的鲸鱼优化算法[J]. 微电子学与计算机, 2017, 34(9): 20-25.
[19]	Wu, P.C. and Huang, K.C. (2006) Parallel Use of Multiplicative Congruential Random Number Generators. Computer Physics Communications, 175, 25-29. [Google Scholar] [CrossRef]