Analysis of Various Feature Selection Techniques for Network Intrusion Detection Dataset in WEKA
Tanya Garg · 2014
As the data on the network is growing day by day, there is requirement of detecting that data for intrusions with high speed and accuracy. These growing Network data is causing a serious problem of detecting intrusions to protect the useful information on the network. There are numerous network security tools to protect network from intrusions but still the fast growth of intrusive activities is a serious issue. Intrusion detection systems (IDSs) are used to detect intrusive activities on the network. Machine learning and Feature Selection Techniques help to design “Intrusion Detection Models” which can classify the network traffic into intrusive or normal traffic. Generally the intrusions are detected by analyzing 41 attributes from the intrusion detection dataset. In this work we tried to reduce the number of attributes by using various ranking based feature selection techniques and evaluation has been done using ten classification algorithms that I have evaluated most important. So that the intrusions can be detected accurately in short period of time. Finally the performance of the six reduced feature sets has been analyzed.