A Novel Framework for Intrusion Detection in Computer Networks by Integrating the Grey Wolf Optimization Algorithm and Random Forest Classification

Intrusion detection in computer networks is one of the most important challenges in the field of computer network security. One of the most successful methods used for intrusion detection in computer networks in recent years is the application of artificial intelligence algorithms, especially the Random Forest (RF) classification algorithm. However, intrusion detection remains a critical challenge. The lack of appropriate training data for training artificial intelligence algorithms is one of the main reasons for the reduction in intrusion detection accuracy in previous studies. In this paper, a novel framework for intrusion detection in computer networks is proposed, in which optimal training data are selected using the Grey Wolf Optimization algorithm to provide suitable training samples for the RF classifier. According to the obtained results, the proposed method improves the accuracy by ۱.۵% and achieves an accuracy of ۹۹.۵%.

کلیدواژه ها:

Intrusion Detection ، Random Forest Classifier ، Grey Wolf Optimization Algorithm ، Training Data Selection