Network Intrusion Detection Based On Immune Clonal Selection Weighted Naive Bayesian Classifier

With the develop of big data,network data grow with each passing day,t he traditional network intrusion detection exist some problems,like collapse,false alarm,failure and other issues.It has been unable to meet the needs of the present stage.Data mining technology has a unique advantage in dealing with large amounts of data,and its influence in the field of network intrusion detection is also growing.As a traditional data mining algorithm,the Naive Bayesian classifier has many advantages,and can well meet the needs of network intrusion detection.But it also has the problem of insufficient accuracy.The following study work has been done in this thesis.Comparatively study different detection object and different classification network intrusion detection,and draw the conclusion that the hybrid detection object and anomaly detection network intrusion detection is more suitable for the current network environment.According to the characteristics of the classic network intrusion detection framework and data mining technology,this thesis puts forward a framework of net work intrusion detection.This thesis makes a deep study on the Naive Bayes classifier and expounds the principle of using it to realize network intrusion detection.Based on Naive Bayesian classifier for network intrusion detection has a disadvantage.Assume that the eigenvalues are independent of each other.In order to solve this problem,proposes a network intrusion detection system based on immune clonal selection algorithm weighted naive Bayesian classifier.The core ideal is the antibody of clonal se lection algorithm as the weight.Increase the relationship by weight,constantly optimize the weights to improve the accuracy of detection by clonal selection algorithm.The KDD99 data set,which is representative in the network intrusion detection field,is used as the training set and test set.The method is tested by MATLAB,and the experimental results are analyzed in detail.The results show that immune clonal selection algorithm weighted naive Bayesian can improve the accuracy of intrusion detection.In order to verify the correctness of the proposed method,the proposed method is verified by MATLAB.Using MATLAB programming to achieve the naive Bayesian classifier and immune clonal selection weighted naive Bias classifier function.The experimental re sults show that the proposed method improves the accuracy of intrusion detection.