نور فؤاد حسين
With the rapid progress in communication and information exchange, the threats have also grown accordingly. Therefore, intrusion detection systems have become a demanded module in terms of computer and network security. In this paper, an intrusion detection model based on genetic algorithm (GA) to detect packets incoming from network traffic into normal and attack is proposed. The proposed algorithm uses Euclidean distance to form normal and attack clusters. Then, the components that characterize the GA based clustering algorithm, including: solution representation, fitness evaluations, and evolutionary operators is applied. The proposed GA based clustering is evaluated to confirm the value of the obtained clustering structures using NSL-KDD benchmark dataset and compared with well- known K-prototypes clustering algorithm. The result in terms of accuracy, detection rate and false alarm rate of the proposed model is better than k-prototypes in all evaluation terms.