Mobile Adhoc Networks - Establishing Initial Risk Profiles utilizing ML Techniques

Abstract

Mobile Adhoc Networks also known as MANETS or Wireless Adhoc networks is a network that usually has a routable networking environment on top of a Link Layer ad hoc network. They consist of a set of mobile nodes connected wirelessly in a self-configured, self-healing network without having a fixed infrastructure. Current bodies of research have given an overview of the studies being done with respect to MANETs in the realm of machine learning. As it pertains to MANET security, a key observation noticed is that, the general direction of research and studies conducted focuses primarily on intrusion detection and malicious node sensors malicious behaviours within MANETs. These trends give a clear indication that a predominantly impact based approach to understanding and addressing risks within MANETs is usually adopted in contemporary studies. To fully address the issue of MANET risks, it is imperative to have a ‘probability vs. impact’ outlook pertaining to the topic. Thus, focus would be placed on how to ascertain risk levels in MANETs by utilizing machine learning probability based techniques. This paper proposes a new method to proactively determine risk levels within MANETs.