摘要
针对入侵检测中网络数据高维度、大规模所带来的问题,基于特征选择方法 Fisher在网络安全数据集中的应用,提出一种基于特征选择的通用入侵检测框架.该方法通过提取关键特征,降低安全数据的维度;采用K近邻方法作为分类器,验证特征选择后的检测效果.实验结果表明,该方法能在较少特征的情况下达到较高的检测率,具有较好的可行性.
This paper concerns about the problems about processing large-scale and high dimension network datasets in intrusion detection.The typical feature selection algorithm Fisher was used in network security datasets,in order to reduce the dimension of features.K-nearest neighbor algorithm was used as the classify algorithm,to evaluate the detection rate.A general intrusion detection framework based on feature selection was presented and realized.Experiments show it has a satisfying detection accuracy with less features and a good feasibility.
出处
《吉林大学学报（理学版）》
CAS
CSCD
北大核心
2015年第1期112-116,共5页
Journal of Jilin University:Science Edition
基金
国家自然科学基金(批准号:61103197)
吉林省重大科技专项基金(批准号:2011ZDGG007)
关键词
入侵检测
Fisher特征选择
K近邻算法
intrusion detection
Fisher feature selection
K-nearest neighbor algorithm
