A Machine Learning Approach to Detect Router Advertisement Flooding Attacks in Next-Generation IPv6 Networks

摘要: Router advertisement (RA) flooding attack aims to exhaust all node resources, such as CPU and memory, attached routers on the same link. A biologically inspired machine learning-based approach is proposed in this study detect RA attacks. The technique exploits information gain ratio (IGR) principal component analysis (PCA) for feature selection a support vector (SVM)-based predictor model, which can also input traffic anomaly. real benchmark dataset obtained from National Advanced IPv6 Center of Excellence laboratory used evaluate technique. evaluation process conducted with two experiments. first experiment investigates effect IGR PCA methods identify most contributed features SVM training model. second evaluates capability results show that demonstrates excellent detection accuracy thus an effective choice detecting main contribution identification set new are related by utilizing algorithms. paper effectively presence network.