A New Approach to Artificial Immune System for Intrusion Detection of the Mobile Ad Hoc Networks

Abstract

The use of artificial immune systems (AIS) in intrusion detection is an attractive concept for several reasons. Then it is judicious to expect that approaches of biological inspirations in this area, and specifically the abstraction of immune defense mechanism with its high detection capabilities and its strong defense against intrusion, will probably be able to meet this challenge. Researchers have implemented different immune models to design intrusion detection systems (IDS) in order to secure Mobile Ad Hoc Networks (MANET), but the most popular one is the self and non-self model. This model was used in the vast majority of biological inspiration in the field of MANET security. It has demonstrated attractive success, as well as it showed some weakness especially in terms of scalability and coverage. This paper try to incorporate some additional concepts proposed by the new danger theory in order to overcome some of the problems related to the adoption of the self and non-selfmodel. The proposed algorithm integrates and combines the basic concepts of intrusion detection system based on the role of T cells described by the negative selection algorithm, with those inspired by the role of dendritic cells to process the alarm signals and to judge thereafter whether there is presence of a dangerous element or not.