作者: Dat Tran , Wanli Ma , Dharmendra Sharma
DOI: 10.1109/SYSOSE.2008.4724144
关键词: Feature (computer vision) 、 Pattern recognition 、 Data mining 、 Computer science 、 Data modeling 、 Anomaly-based intrusion detection system 、 Fuzzy set 、 Vector quantization 、 Artificial intelligence 、 Feature extraction 、 Intrusion detection system 、 Weighting
摘要: A common problem for network intrusion detection systems is that there are many available features describing traffic and feature values highly irregular with burst nature. Some such as octets transferred range several orders of magnitudes, from bytes to million bytes. The role depends on which pattern be detected: normal or intrusive one. Intrusion rates would better if we know more important a particular pattern. We therefore propose an automated weighting method based fuzzy subspace approach. Experimental results show the proposed can improve rates.