The Research Of Intrusion Detection Model Based On Neural Network

Nowadays, the network security question has been prominent more and more. Intrusion Detection System has become the essential security means. The so-called intrusion detection is to detect and identify the illegal attack and intrusion behavior that aim at the computer system, information system and the network. This technique has been used to protect the information of the companies in the world. But the traditional IDS still has flaw such as slow detection speed and high leaks detection rate.Firstly, this paper analyzed the traditional IDS structure and the detection method, and researched the application of NN in IDS. To speed up the detection speed, enhances accurately rate, a new IDS model base on NN is presented. This model use BP neural network to detect the intrusion, it transforms the pattern recognition as the value computation, thus sped up the detection speed, simultaneously; the expert system assisted to detect and provide the real time train sample to the NN, thus enhanced the accurate rate.Secondly, to solve the problem of the BP NN in the practical application, the BP algorithm has been thorough researched. At first, to speed up the convergence rate, and solve the vibration of the optimal solution. The auto-adapted adjustment study algorithm and the attachment momentum algorithm were used. Secondly, to solve the problem that all the parameter value must be adjusted by each training sample, the path stimulation algorithm was used to ignored the effect of the minimum, so that the training efficiency was enhanced.Finally, as the application of the research, by using the VC6.0 and the reasonable construction of data, an intrusion detection prototype system based on the neural network was implemented. And under the local area network, testthe prototype system with the mass data. The result has confirmed the system performance and efficiency...