Artificial Immune System Inspired Intrusion Detection System Using Genetic Algorithm

Computer security is an issue that will always be under investigation as intruders never stop to find ways to access data and network resources. Researches try to find functions and approaches that would increase chances to detect attacks and at the same time would be less expensive, regarding time and space. In this paper, an approach is applied to detect anomalous activity in the network, using detectors generated by the genetic algorithm. The Minkowski distance function is tested versus the Euclidean distance for the detection process. It is shown that it Minkowski distance give better results than the Euclidean distance, and can give very good results using less time. It gives an overall average detection rate of 81.74% against 77.44% with the Euclidean distance. In addition, formal concept analysis was applied on the data set containing only the selected features and used to visualize correlation between highly effective features.