INTELLIGENT NETWORK INTRUSION DETECTION SYSTEM BASED ON ARTIFICIAL IMMUNE SYSTEM MECHANISMS
The article is devoted to the problem of detecting network attacks, both known and previously unknown. The application of various methods of artificial intelligence in the scientific literature to solve this problem was analyzed. The advantages of the artificial immune system were revealed. Its main mechanisms including artificial lymphocytes generation, negative selection, clonal selection, data analysis, and periodic renewal of lymphocytes were analyzed. The article describes the developed intrusion detection system based on artificial immune system. Developed system includes a sniffing subsystem, so that allows it to analyze real data of host network connections. The article also describes network connections dataset KDD99, which used to efficiency evaluation of developed system. The methods of compressing the initial dataset proposed in the scientific literature were analyzed, and the drawbacks of these methods were identified. This article describes the experimental determination of the network connections significant parameters contained in the dataset. The authors identified 13 significant parameters from 41, and also they described the process of preliminary processing and preparation of the analyzed data, a series of experiments. The results of the experiments showed the high efficiency of the developed system in detecting unknown network attacks, detecting and classifying known attacks.
Keywords: : intrusion detection system, artificial immune system, KDD99, information security, network security, network attack.