T-Cell detector maturation algorithm based on cooperative co-evolution GA

Abstract

Efficient T-cell detector maturation algorithm is one of the most important problems of anomaly detection. Aiming at solving problems of current algorithms, such as low TP value, fixed matching threshold value and large detector set size. A novel T-detector maturation algorithm based on cooperative co-evolution genetic algorithm is put forward in this paper. According to morphologic analysis of intrusion detection system and covering problem algorithm. And then each population evolves according to each self partition and their best population would be combined as the final matured detector set, which decreases redundancy of detectors and maintains diversity of detectors. The efficiency is proved by theoretical foundation and tests.