Analyzing Attacks in Wireless Ad Hoc Network with Self-Organizing Maps

Abstract

Detecting anomalous events and attacks in the ad-hoc wireless network is a challenging area for research due to the characteristics of wireless network. The proposed detection system monitors network traffic on each node and analyzes collected data by self-organizing maps to extract statistical regularities from the input data vectors and encode them into the weights without supervision. We evaluate our approach to detect network attacks on AODV and DSR protocols using OPNET. Our simulation results show that our approach can accurately detect anomalous behaviors caused by network attacks.