摘要
Support vector machine (SVM) technique has recently become a research focus in intrusion detection field for its better generalization performance when given less priori knowledge than other soft-computing techniques. But the randomicity of parameter selection in its implement often prevents it achieving expected performance. By utilizing genetic algorithm (GA) to optimize the parameters in data preprocessing and the training model of SVM simultaneously, a hybrid optimization algorithm is proposed in the paper to address this problem. The experimental results demonstrate that it’s an effective method and can improve the performance of SVM-based intrusion detection system further.
Support vector machine （SVM） technique has recently become a research focus in intrusion detection field for its better generalization performance when given less priori knowledge than other soft-computing techniques. But the randomicity of parameter selection in its implement often prevents it achieving expected performance. By utilizing genetic algorithm （GA） to optimize the parameters in data preprocessing and the training model of SVM simultaneously, a hybrid optimization algorithm is proposed in the paper to address this problem. The experimental results demonstrate that it＇s an effective method and can improve the performance of SVM-based intrusion detection system further.
基金
This work was supported by the Research Grant of SEC E-Institute :Shanghai High Institution Grid and the Science Foundation ofShanghai Municipal Commission of Science and Technology No.00JC14052
关键词
支持向量机
组合最优化
入侵检测系统
遗传算法
系统调用踪迹
连续最小最优化
intrusion detection system （ IDS） , support vector machine （ SVM） , genetic algorithm （ GA ） , system call trace, ξα-estimator , sequential minimal optimization（SMO）
