ELM based Ensemble of Classifiers for BGP Security against Network Anomalies

Abstract

The Border Gateway Protocol (BGP) is an essential element of the Internet infrastructure, playing a crucial role in ensuring global connectivity and stability for smooth communication. Numerous techniques are created by the researchers to detect anomalies in the network for enhancing stability of the BGP network (BGP based environment). On the other hand, the dynamic nature and intricate structure of the network poses challenges in identifying attacks environment. As a result, applying a single classifier to classify them is a challenging task. In this paper a method based on ensemble learning is proposed where Extreme Learning Machine (ELM), K-Nearest Neighbor (KNN), and Naive Bayes (NB), classifiers are ensembled to detect the attacks in BGP based environment. The proposed approach is evaluated on Reseaux IP Europeens (RIPE) and British Columbia’s Advanced Network (BCNET) datasets and compared with other recent approaches. On investigating the results, it is found that the proposed approach is providing better performance on both datasets.