What is it about?
The Border Gateway Protocol (BGP) is an important routing protocol that binds the Internet, and it remains vulnerable despite security advancements. The novel application of a data mining approach, Matrix Profile (MP), to detect BGP anomalies is reported on in this paper. Current detection schemes are dominated by computationally complex and costly techniques. Advantages of the MP detection technique include that it is domain agnostic, is assumption-free, requires few parameters, does not require training data, and is scalable and storage efficient.
Featured Image
Photo by Mel Poole on Unsplash
Why is it important?
The machines (routers) that speak BGP require computationally efficient detection techniques. The data mining technique reported on in this paper provides for a number of computationally efficient advantages. Our results indicate the MP detection technique is competitive against existing detection methods.
Perspectives
The ‘glue’ that binds the Internet (BGP) is the most important communication protocol many people have never heard of. This remains the case despite social media platforms, entire Internet Service Providers (ISPs), and telecommunications companies brought down by BGP vulnerabilities.
Ben Scott
Edith Cowan University
Read the Original
This page is a summary of: Matrix Profile data mining for BGP anomaly detection, Computer Networks, April 2024, Elsevier,
DOI: 10.1016/j.comnet.2024.110257.
You can read the full text:
Contributors
The following have contributed to this page
