intrusion detection system in computer networks using decision tree and svm algorithms

internet applications spreading and its high usage popularity result insignificant increasing of cyber-attacks. consequently, network security has becomea matter of importance and several methods have been developed for these attacks.for this purpose, intrusion detection systems (ids) are being used to monitor theattacks occurred on computer networks. data mining techniques, machinelearning, neural networks, collective intelligence, evolutionary algorithms andstatistical methods are some of algorithms which have been used for classification,training and reviewing detection accuracy with analysis based on the standarddatasets in intrusion detection systems. in this paper, the hybrid algorithm isintroduced based on decision tree and support vector machine (svm) using featureselection and decision rules to apply on ids. the main idea is to use the strengths ofboth algorithms in order to improve detection, enhance the accuracy and reduce therate of error detection of the results. in this algorithm, the best features are selectedby svm, afterwards decision tree is used to make decisions and define rules. theresults of applying proposed algorithm are analyzed on the standard dataset kddcup99. the proposed method guarantees high detection rate which is proved bysimulation results.