A New Feature Selection Method for Intrusion Detection

Intrusion detection is an effective measure to prevent host and network attacks. The use of an intrusion detection system makes up for the shortcomings of traditional firewall technology, signature authentication technology, and access control technology in security protection. However, due to the imbalance of the distribution of intrusion detection data samples, the mutual redundancy between sample features seriously affects the accuracy and efficiency of specific attack detection. In this paper, a proposal was forward, the appropriate feature subsets are selected respectively based on mutual information and the firefly algorithm, and then proposed a feature selection strategy combining two feature subsets. Experiment outcomes show that the accuracy and efficiency of detection are improved by using the best feature set, compared to the use of all features.