抽象的な

Architecture of Hybrid Intrusion Detection System using TAN & GA Algorithm

Namita Parati, Sumalatha Potteti

The dramatically development of internet, security of network traffic is becoming a major issue of computer network system. Attacks on the network are increasing day-by-day. Many intelligent learning techniques of machine learning are applied to the large volumes of data for the construction of an efficient intrusion detection system (IDS). Several machine-learning paradigms including neural networks, linear genetic programming (LGP), support vector machines (SVM), Bayesian networks, multivariate adaptive regression splines (MARS) fuzzy inference systems (FISs), etc. have been investigated for the design of IDS. This paper presents an overview of intrusion detection system and a hybrid technique for intrusion detection based on . Tree Augmented Naïve Bayes (TAN) algorithm and Genetic algorithm. TAN algorithm classifies the dataset into various categories to identify the normal/ attacked packets where as genetic algorithm is used to generate a new data by applying mutation operation on the existing dataset to produce a new dataset. Thus this algorithm classifies KDD99 benchmark intrusion detection dataset to identify different types of attacks with high detection accuracy. The experimental result also shows that the accuracy of detecting attacks is fairly good.