Research On The Application Of Data Mining In Intrusion Detection

The network complexity is on the increase. The network security is being paid close attention to. We need a system which can find hostility behavior and take action before it do harm to the system and date, so intrusion detection system will give play to irreplaceable function. Intrusion detection has become a strong barrier to defend net intrusion because of initiative recovery strategy of focusing on data analyzing. As a kind of active measure of Information assurance, Intrusion Detection acts as the effective complement to traditional protection techniques. Data mining, an effective technique in data analyzing, is naturally applied in intrusion detection Therefore, researching of intrusion detection system basing on data mining become more and more hot.The core of this thesis is the Research and Application of Data-mining based Intrusion Detection System. The existing Data-mining technology and Intrusion Detection System technology were analyzed and compared, the clustering algorithm was discussed. And the advantages of the technology were indicated. a improved fuzzy C-means clustering algorithm is put forward. The basic idea of the algorithm is using Mahalanobis space and modified by changing the object vector to matrix to adapted algorithm to more data model.In this paper, we analyze the characteristic of the intrusion detection technique, and bring forward approach of network intrusion detection based on the improved fuzzy C-means clustering. The benefit of this approach is that it need not labeled training data sets. Using the data sets of KDD99, the experiment result shows that this approach can detect unknown intrusions efficiently, and increase detection rate of the clustering detection and decrease the false alarms rate.