A New Intrusion Prediction Method Based on Feature Extraction

In order to find the attack in real time, an intrusion prediction method based on feature extraction algorithm was presented. Using CHI approach, the fields of network packet, which were irrelevant with attack type, were deleted, and the representative fields were selected to form feature database. Moreover, optimization extraction function was obtained by normalization method, and then network packets were effectively classified into normal or anomalous by the classifier. Experiment analysis proves that this intrusion prediction method have relatively low false positive rate and false negative rate, thus it effectively resolves the shortage of intrusion detection.