Using Genetic Feature Selection for Improving Cyber Attack Detection Rate

C.H. Lee, D.H. Lee, and J.W. Chung (Korea)


Cyber attack, network intrusion, data mining, genetic algorithm, feature selection.


As Internet becomes an essential tool for all kinds of business transactions, the issue for detecting network intrusion has received greater attention. In this paper, we suggest a novel method based on a genetic optimization that can improve the detection rate for attack patterns without a loss due to false-positive error rate. We focus on selecting a robust feature subset by designing a multi criteria optimization procedure. During the evaluation phase, the performance of proposed approach is contrasted against one of the state-of-the-art feature selection methods using a k nearest neighbor classifier. Experimental results show that the proposed approach is remarkably effective than using the full feature set.

Important Links:

Go Back