1. 郑州航空工业管理学院 机构 航空工程系,河南,郑州,450015
2. 航空经济发展河南省协同创新中心,河南,郑州,450046
3. 空军工程大学 机构 防空反导学院,陕西,西安,710051
纸质出版:2016
移动端阅览
魏振伟, 刘飞. 粒子群特征优选的SVDD入侵检测研究[J]. 微电子学与计算机, 2016, 33(8): 144-148.
WEI Zhen-wei, LIU Fei. Research of Network Intrusion Detection Based on Particle Swarm Optimization and Support Vector Data Description[J]. 2016, 33(8): 144-148.
针对入侵检测中样本集维数较高问题
提出一种基于粒子群算法(PSO)优化的支持向量数据描述(SVDD)方法
将其应用于网络异常入侵检测.该方法采用粒子群算法消除支持向量数据描述中的冗余参数并对数据降维
并建立SVDD超球体模型
对网络入侵数据进行检测并输出入侵检测结果.在KDD CUP’99的标准检测数据集上进行仿真实验
结果表明该方法和传统的SVDD相比不仅能够有效提高检测率
而且计算量较小.
Concerning the data set of high dimensions in intrusion detection
the new algorithm based on support vector data description (SVDD) which optimized by particle swarm optimization (PSO) was proposed. In the improved algorithm
at firstly the particle swarm optimization was used to remove redundant features and reduce the data dimension in support vector data description. And then
the support vector data description built a super sphere model to detect the attacks from internet by analyzing the network connection data. Results from the experiments with the KDD CUP99 network data indicate that the method of PSO-SVDD is better than traditional one class classifiers algorithm
which can improve the efficiency of intrusion detection and reduce the false detection rate.
Tax D M J, Duin R P W. Support vector data description[J]. Machine Learning, 2004, 54(1): 45-66. DOI: 45
刘宇, 朱随江, 刘宝旭. 采用改进PTSVM的入侵检测研究[J]. 计算机工程与应用, 2012, 48(5): 1-3, 74. DOI: 1
Mahbod Tavallace, Ebrahim Bagheri, Wei Lu, et al. A Detailed Analysis of the KDD CUP 99 Data Set[C]// Proceeding of the Setonal IEEE International Conference on Computational Intelligence for Security and Defense Applications. [s. l. ]: IEEE, 2009: 1-10.
饶鲜, 董春曦, 杨绍全. 基于支持向量机的入侵检测系统[J]. 软件学报, 2003, 14(4): 798-802. DOI: 798
金欣磊, 马龙华, 吴铁军, 等. 基于随机过程的PSO收敛性分析[J]. 自动化学报, 2007, 33(12): 1263-1268. DOI: 1263
梁海军. 人工蜂群优化支持向量机算法在网络安全中的应用[J]. 微电子学与计算机, 2013, 30(2): 95-98. DOI: 95
0
浏览量
12
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号