Abstract:
This paper proposes a method for intrusion detection based on Boosting fuzzy classification. Fuzzy rules involved in intrusion detection are obtained by genetic algorithm, and Boosting algorithm is employed to change the distribution of training instances during each round of training, so that new fuzzy classification rules extracted by genetic algorithm will put more emphasis upon the instances misclassified or uncovered. Simulation experiments with the data set kddcup’99 show that the method has good recognition performance.
Key words:
fuzzy classification,
genetic algorithm,
Boosting algorithm,
intrusion detection
摘要: 提出一种基于Boosting模糊分类的入侵检测方法。采用遗传算法来获取入侵检测的模糊规则,利用Boosting算法不断改变训练样本的分布,使每次遗传算法产生的模糊分类规则重点考虑误分类和无法分类的样本。以kddcup’99为数据源进行了仿真实验,结果表明该方法具有良好的分类识别性能。
关键词:
模糊分类,
遗传算法,
Boosting算法,
入侵检测
CLC Number:
TANG Xiao-heng; XIA Li-min. Intrusion Detection Based on Boosting Fuzzy Classification[J]. Computer Engineering, 2008, 34(5): 225-227.
唐晓衡;夏利民. 基于Boosting模糊分类的入侵检测[J]. 计算机工程, 2008, 34(5): 225-227.