A feature selection model based on genetic algorithm for intrusion detection

Abstract EN

Now days, it is very important to provide a high level of security for huge amount of information transferred in the network to protect them from threats.

Due to that, an intrusion detection system (IDS) becomes a required component in terms of computer and network security.

One of the biggest challenges for IDS is the high dimensionality of the feature space and how to select the relevant features to distinguish the normal network packet from attack network packet.

In this paper, an optimization model based on genetic algorithm (GA) to select the distinguished features for intrusion detection is proposed.

Moreover, the Naïve Bayes (NB) classifier is applied to judge the ability of the proposed model to classify normal and attack network packets.

The performance of the proposed model is evaluated against information gain algorithm (IG).

The experiments on NSL-KDD benchmark dataset reveal the effectiveness of the proposed model to detect attack and normal network packets.-