Dynamic Neural Networks in the Detection of Distributed Attacks in Mobile Ad-Hoc Networks

Download Now Date Added: Jan 2010
Format: PDF

This paper describes the latest results of a research program that is designed to enhance the security of wireless Mobile Ad Hoc NETworks (MANET) by developing a distributed intrusion detection capability. The current approach uses learning vector quantization neural networks that have the ability to identify patterns of network attacks in a distributed manner. This capability enables this approach to demonstrate a distributed analysis functionality that facilitates the detection of complex attacks against MANETs. The results of the evaluation of the approach and a discussion of additional areas of research are presented.