摘要
利用改进算法的学习能力和快速识别能力,实现了对用户行为的检测,尤其是在识别以前没有观察到的未知攻击方面具有较好的性能。
A new neural network-based intrusion detection approach is proposed.This approach employs the improved algorithm that provides the capability of learning and quick classification, and can be used for detection of user behavior. In particular, this approach gains good performance in recognizing future unseen attacks.
出处
《武汉理工大学学报（信息与管理工程版）》
CAS
2005年第2期142-145,共4页
Journal of Wuhan University of Technology：Information & Management Engineering
关键词
入侵检测
神经网络
特征提取
拆分与组装
intrusion detection
neural network
feature extraction
split and assembling
