As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This paper presents a network intrusion detection technique based on Synthetic Minority Over-Sampling Technique (SMOTE) and Deep Belief Network (DBN) applied to a class imbalance KDD-99 dataset. SMOTE is used to eliminate the class imbalance problem while intrusion classification is performed using DBN. The proposed technique first resolves the class imbalance problem in the KDD-99 dataset followed by DBN to estimate the initial model. The accuracy is further enhanced by using multilayer perceptron networks. The obtained results are compared with the existing best technique based on reduced size recurrent neural network. The study shows that our approach is competitive and efficient in classifying both intrusion and normal patterns in KDD-99 dataset.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.