Intrusion Detection Neural Network And Ds Theory

With the development of the application of Internet, network security becomes more and more important. Intrusion detection systems that parallel the firewalls and encryption systems are prosperous, it's necessary to employ active security resolution to detection intrusion and protect network resources in time.However as a new network security technology,inrusion detection technology has become the major concern of network security reaseraching field.Artificial Neural Network (ANN) is a new type of intelligence system, which imitates the biological neural constructure.It is a nerve-unit-linked network based on the theory of biology nerve nets. It mainly researches the information distributation and signal process in the complicated multi-dimensional non-linear system, also the principle and method of signal processing, at the same time, applies them to solving the practical problems in engineering. The research on this subject combines the practical problem in engineering. The research on this subject combines the foundamental subjects such as biology, cognitive science, non-liner science with these engineering subjects like computer, electronics, AI, information processing, model recognizing and so on. It has a bright applying promise.This paper implement three group intrusion detection by applying neural network base on class of test data of MIT Lincoln Lab. then uses D-S evidence theory method to enforce data fusion upon detection result to get higher detection precision.The primary work:Base on feature of intrusion test data of MIT Lincoln Lab, Pretreatment of test data and classed based on the feature attribute of network connect.Train neural network and get primary result data of intrusion detection., get the finally conclusions and enforce high detection precision by using D-S evidence theory.At last, make a summary of shortage of research and farther work and discuss the way and the development of the unborn intrusion detection technology.