| 基于多分类支持向量机的网络入侵检测技术 |
| |
| 引用本文： | 李健,范万春,何驰. 基于多分类支持向量机的网络入侵检测技术[J]. 计算机应用, 2005, 25(7): 1551-1553,1561 |
| |
| 作者姓名： | 李健 范万春 何驰 |
| |
| 作者单位： | 西北核技术研究所,陕西,西安,710024;西北核技术研究所,陕西,西安,710024;西北核技术研究所,陕西,西安,710024 |
| |
| 摘 要： | 对多分类支持向量机在网络入侵检测中的应用进行了研究，深入探讨了其中的关键技术问题和解决方法，并用KDD1999CUP中的标准入侵检测数据集对文中设计的支持向量机分类器进行了测试评估，将实验结果和BP神经网络方法进行了比较。实验证明，该方法在保持较低误警率的同时有着很好的检测率，并且在训练时间上优于BP网络方法。
|
| 关 键 词： | 统计学习理论 支持向量机 入侵检测 特征选择 |
| 文章编号： | 1001-9081(2005)07-1551-03 |
Network intrusion detection based on multi-class support vector machine |
| |
| LI Jian,FAN Wan-chun,He Chi. Network intrusion detection based on multi-class support vector machine[J]. Journal of Computer Applications, 2005, 25(7): 1551-1553,1561 |
| |
| Authors: | LI Jian FAN Wan-chun He Chi |
| |
| Abstract: | The application of multi-class support vector machine(SVM) for network intrusion detection was researched, and the key technique problems and solutions were discussed. Our designed SVM classifier was evaluated with a benchmark dataset used in the third knowledge discovery and data mining competition (KDD'99), the results obtained were compared with BP neural network's. Experiment results show that classifier based on SVM outperforms BP neural network in training time. |
| |
| Keywords: | statistical learning theory support vector machines(SVM) intrusion detection feature selection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
