Application of Immune Algorithm to Generate Fuzzy-Detector in Intrusion detection

The neglect of the fuzzy limit between the self and non-self gave the poor efficiency of detection, where traditional negative selection algorithm was used in intrusion detection. And the computational complexity by using large numbers of detectors was too high. Aiming at these flaws, it´s necessary to press emphasis on the fuzzy detection rules, and a hybrid approach is proposed which uses the searching performance of immune algorithm to generate fuzzy-detectors. The results of the experiment prove that fuzzy rules express the self/non-self compactly, reduce the frangibility of detectors greatly and have an exciting featureae.