Improving ID performance using GA and NN

摘要

The internet has been growing at an amazing rate and concurrent with the growth, the vulnerability is also increasing. How to find and detect novel or unknown attacks is one of the most important objectives in current IDS. Most of the current IDS examine all data features to detect intrusions. However, some of the features may be redundant or contribute little to the detection process. This paper mainly addresses the issue of identifying important input features for intrusion detection. This paper proposes an intrusion detection model that is computationally efficient and effective based on mutual information. Then genetic algorithm is applied to generate optimal rules. Those generated rules are used to detect known attacks. RBF is also used to learn and detect unknown attacks. Experimental results on the well-known KDD 99 data set show the achievement of high true positive rates and acceptable low false positive rates and are effective.