An Effective DoS Prevention System to Analysis and Prediction of Network Traffic Using Support Vector Machine Learning
Anil Kumar Sharma, Pankaj Singh Parihar · 2013
Mobile Ad Hoc Networks has more susceptible towards vulnerabilities compared with wired networks. MANET has become an important technology in current years because of the rapid explosion of wireless devices. They are highly susceptible to attacks due to the open medium, dynamically changing network topology. MANETs have unique characteristics like dynamic topology, wireless radio medium, limited resources and lack of centralized administration; as a result, they are vulnerable to different types of attacks in different layers of protocol stack. Each node in a MANET is capable of acting as a router. Routing is one of the aspects having various security concerns. There are various common Denial-of-Service (DoS) attacks occurs on network layer namely Wormhole attack, Blackhole attack and Grayhole attack which are serious threats for MANETs. It is required to search new architecture and mechanisms to protect these networks. With continuous scale-up of the network and increase of the kinds of the services on the network, more and more people pay attention to the modeling and prediction for network traffic. Recently, SVM Support Vector Machine), a new machine learning method, is comprehensively used to solve the problem of non-liner classification and regression. Support vector machines (SVM) are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. The basic SVM takes a set of input data and predicts, for each given input, which of two possible classes forms the output, making it a nonprobabilistic binary linear classifier. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples into one category or the other. An SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. A network traffic predictive method presented in this paper is based on the LS-SVM (Least Squares SVM). In machine learning, the (Gaussian) radial basis function kernel, or RBF kernel, is a popular kernel function. It is the most popular kernel function used in support vector machine classification. The RBF kernel on two samples x and x', represented as feature vectors in some input space. A network traffic predictive method presented in this paper is based on the SVM. Using NS2 simulator, we simulate the process of the network.