Performance analysis of artificial neural network intrusion detection systems
Mohamed Abdelazim, A. I. Abdel-Fatah, Mohamed M. Awad · International Conference on Electrical and Electronics Engineering · 2009
Intrusion detection is the art of detecting computer abuse and any attempt to break into networks. As a field of research, it must continuously change and evolve to keep up with new types of attacks or adversaries and the ever-changing environment of the Internet. To render networks more secure, intrusion-detection systems (IDSs) aim to recognize attacks within constraints of two major performance considerations: high detection and low false-alarm rates. It is also not enough to detect already-known intrusions, yet-unseen attacks or variations of those known present a real challenge in the design of these systems. IDSs are firmly entrenched on the security front but the exact role they can play and what their deployment entails must be clear to planners of security. Nine artificial neural networks (ANN) based IDS were implemented and tested with three experiments with three topologies. The results showed that: (i) in average the modular neural network (MNN) provided the best results in experiment#3; about 99.60%; (ii) in average multilayer perceptron (MLP) provided the best results in experiment#2; 74.71%; (iii) in experiment#1; the MNN provided the best results.