Multimodal Evolution Approach to Multidimensional Intrusion Detection

An artificial immunity based multimodal evolution algorithm is developed to generate detectors with variable coverage for multidimensional intrusion detection. In this algorithm, a proper fitness function is used to drive the detectors to fill in those detection holes close to self set or among self spheres, and genetic algorithm is adopted to reduce the negative effects that different distribution of self imposes on the detector generating process. The validity of the algorithm is tested with spherical and rectangular detectors, respectively, and experiments performed on two real data sets （machine learning database and DAPRA99） indicate that the proposed algorithm can obtain good results on spherical detectors, and that its performances in detection rate, false alarm rate, stabih＇ty, time cost, and adaptability to incomplete training set on spherical detectors are all better than on rectangular ones.

Multimodal Evolution Approach to Multidimensional Intrusion Detection

An artificial immunity based multimodal evolution algorithm is developed to generate detectors with variable coverage for multidimensional intrusion detection. In this algorithm, a proper fitness function is used to drive the detectors to fill in those detection holes close to self set or among self spheres, and genetic algorithm is adopted to reduce the negative effects that different distribution of self imposes on the detector generating process. The validity of the algorithm is tested with spherical and rectangular detectors, respectively, and experiments performed on two real data sets (machine learning database and DAPRA99) indicate that the proposed algorithm can obtain good results on spherical detectors, and that its performances in detection rate, false alarm rate, stability, time cost, and adaptability to incomplete training set on spherical detectors are all better than on rectangular ones.