Selection of effective network parameters in attacks for intrusion detection

摘要: Current Intrusion Detection Systems (IDS) examine a large number of data features to detect intrusion or misuse patterns. Some the may be redundant with little contribution detection process. The purpose this study is identify important input in building an IDS that are computationally efficient and effective. This paper proposes investigates selection effective network parameters for detecting intrusions extracted from Tcpdump DARPA1998 dataset. Here PCA method used determine optimal feature set. An appropriate set helps build decision model as well reduce population Feature reduction will speed up training testing process attack identification system considerably. dataset was experiments test data. Experimental results indicate time while maintaining accuracy within tolerable range.