Abstract:
This paper introduces danger theory in Artificial
Immune System as a method of responding to danger in
wireless mesh networks. It identifies the challenges in
deploying Wireless Mesh Networks (WMNs) and focus on
secure routing as one of the key challenges in deploying WMNs.
In order to implement a secure routing system, various
Artificial Immune System (AIS) models were analysed. These
models have been used in Intrusion Detection System (IDS)
and computer security in the literature. In this paper, the
authors propose to use Danger models to secure routing in
WMNs. The first step in secure routing process is to identify
and classify the network dangers and take necessary actions to
overcome those dangers. For the classification task, we apply
Self-organizing Maps (SOMs) as the classifier to classify the
danger levels in WMNs. These identified danger conditions are
further deployed as the warning signals for the design of secure
routing protocol. The experimental results validate the
proposal of applying the Danger Theory (DT) into security
area and good performance is also reported by the use of
Artificial Neural Network (ANN) classifier.
