Scrutinizing and evaluating intrusion detection approaches based on the artificial immune system

In recent years, research works in field of the network security have been directed to inspire from biological immune system so as to solve complex problems. Artificial immune system (AIS) and its applied immunity potential with prerequisite for bio defense, is always involved as a method for organization’ security control and network anomaly detection. In this research, different immunity methods in comparison with other machine learning and meta-heuristic algorithms have been analyzed for our main purpose; that is to provide a novel approach for solving the intrusion detection. All of evaluations accomplished on WEKA data mining tool v3.6 under NSL-KDD dataset. Results of experiment show that the AIS methods ARIS2Parallel, Immunos99 and CSCA cause to enhance in accuracy rates sensibly after feature selection phase was embedded to them. So, approach of Bat+ARIS2Parallel with correlation coefficient of 0.946, detection rate of 0.973, accuracy rate of 0.9725 and false positive rate of 0.028 has obtained an idealistic classification compared to other approaches in tests. Since it has high cc rate, it seems that is reliable to be used in researches for IDS developments in future.