Ad hoc-Based Feature Selection and Support Vector Machine Classifier for Intrusion Detection

摘要：

In order to gain the result of identifying a good detection mechanism in intrusion detection, several intelligent techniques such as ANNs, SVMs, and data mining techniques are being used to build IDSs. Instead examining all data features to detect intrusion or misuse patterns, the approach of Adhoc-based feature selection and support vector machine classifier for detect intrusion is performed. In this performance of IDS, Ad hoc technology is used to optimize the feature subset for raw data and 10-fold cross validation is used to optimize the parameters of SVM for intrusion detection. The result of our experiments shows that the FS & SVM is not only superior to the famous data mining strategy, but also superior to other intelligent paradigms.

作者: XIAO Haijun PENG Fang WANG Ling LI Hongwei

作者单位: China University of Geosciences, Wuhan, 430074, China Wuhan Technology Institute, Wuhan, 430074, China

会议类型: 国际会议

会议名称: 2007年IEEE灰色系统与智能服务国际会议(2007 IEEE International Conference on Grey Systems and Intelligent Services)

会议地点: 南京

会议语种:英文

在线出版日期: 2007-11-18（万方平台首次上网日期，不代表论文的发表时间）