His approach machine learning is discussed in a paper entitled "Profiling BGP Serial Hijackers: Capturing Persistent Misbehavior in the Global Routing Table" and will be presented at a conference in Amsterdam later in October.
ISPs can understand it Border Gateway Protocol (BGP), incorrectly announcing the IP address blocks of another network, causing traffic to be redirected. This has previously cost huge amounts of money on Amazon, Google and Google Microsoft.
To this end, the MIT research team conducted a study called “serial BGP hijackers”. In this case, she was examining cases of misconduct associated with Autonomous System numbers. AS is the way they are ISPs are recognized in the BGP route tables.
Although hijacking is usually done by mistake, MIT researchers have investigated a machine learning approach to identify ISPs that perform hijacking frequently over the years. The purpose is that one system detection will allow network engineers to anticipate incorrect announcements and react faster to hijacking events.
The National Institute of Standards and Technology USA (NIST) calls for a public-key cryptographic system that will allow large networks and ISPs to control which networks can communicate a direct connection to address blocks. NIST also processes BGP validation so that routers can filter out unauthorized BGP route announcements.
These measures could alleviate BGP hijacking, however, until this happens researchers work to improve detection and reaction time.
One of the confusing hijackers involved in the study was AS197426, a Portuguese ISP called BitCanal, due to multiple hijacking over the years.
There is a theory that MIT research has the potential to judge them ISP based on their behavior over the years and not just looking at individual cases.