Application of Graph Neural Networks for Representing and Analyzing Internet Topology via the BGP Protocol
Abstract
The relationships between Autonomous Systems (ASes) are a crucial aspect of the Internet, as they reveal how it operates and influences the routing decision, as well as identifying BGP anomalies. However, most of the time this information is confidential, given that each AS is independently managed by different entities. This work aims to infer the types of relationships between ASes using Graph Neural Networks (GNN). The Type of Relationship (ToR) problem has been a topic studied for the past two decades, with most solutions being heuristic. One of the biggest challenges this problem presents is the lack of ground truth information to validate the results. Our preliminary results show an accuracy of accuracy of 0.943 for binary classification and 0.936 for multiclass classification.
