Coevolutionary-based Mechanisms for Network Anomaly Detection

The paper presents an approach based on the principles of immune systems
applied to the anomaly detection problem. Flexibility and efficiency of the
anomaly detection system are achieved by building a model of the network
behavior based on the self-nonself space paradigm. Covering both
self and nonself spaces by hyperrectangular structures is proposed.
The structures corresponding to self-space are built using a training
set from this space. The hyperrectangular detectors covering nonself
space are created using a niching genetic algorithm. A coevolutionary
algorithm is proposed to enhance this process. The results of
experiments show a high quality of intrusion detection, which
outperform the quality of the recently proposed approach based on
a hypersphere representation of the self-space.