Evolutionary computation techniques for intrusion detection in mobile ad hoc networks

Intrusion detection on mobile ad hoc networks (MANETs) is difficult. This is because of their dynamic nature, the lack of central points, and their highly resource-constrained nodes. In this paper we explore the use of evolutionary computation techniques, particularly genetic programming and grammatical evolution, to evolve intrusion detection programs for such challenging environments. Cognizant of the particular importance of power efficiency we analyze the power consumption of evolved programs and employ a multi-objective evolutionary algorithm to discover optimal trade-offs between intrusion detection ability and power consumption.