The application of Hybrid Neural Network Algorithms in Intrusion Detection System

Based on the advantages and disadvantages of the improved GA and LM algorithm, in this paper, the Hybrid Neural Network Algorithm (HNNA) is presented. Firstly, the algorithms use the advantage of the improved GA with strong whole searching capacity to search global optimal point in the whole question domain. Then, it adopts the strongpoint of the LM algorithm with fast local searching to fine search near the global optimal point. The paper used respectively the three algorithms, namely the Improved GA, LM algorithm and HNNA, to adjust the input and output parameters of the ANN model, and adopt the theories of the fusion of the multi-classifiers to structure the Intrusion Detection System. By repeatedly experiment, it is found that the HNNA is better in stability and convergence precision than LM algorithm and improved GA from the training result. The testing results are also proved that the detection rate of the multiple classifiers intrusion detection system based on HNNA learning algorithm, including all attack categories that has a few or many training samples, is higher than the IDS that use LM and improved GA learning algorithm, and the false negative rate is less. So, the HNNA is proved to be feasible in theory and practice.