A Scalable Approach to Network Traffic Classification for Computer Network Defense using Parallel Neural Network Classifier Architectures

View Sample PDF

Author(s): Bereket M. Hambebo (Florida Institute of Technology, USA), Marco Carvalho (Florida Institute of Technology, USA)and Fredric M. Ham (Florida Institute of Technology, USA)
Copyright: 2013
Pages: 16
Source title: Efficiency and Scalability Methods for Computational Intellect
Source Author(s)/Editor(s): Boris Igelnik (BMI Research, Inc., USA)and Jacek M. Zurada (University of Louisville, USA)
DOI: 10.4018/978-1-4666-3942-3.ch009

Keywords: Artificial Intelligence / Computational Intelligence / Computer Science & IT / Information Science Reference

Purchase

View A Scalable Approach to Network Traffic Classification for Computer Network Defense using Parallel Neural Network Classifier Architectures on the publisher's website for pricing and purchasing information.

Abstract

The ability to recognize network traffics plays an important role in securing modern computer network infrastructures. In this chapter, we propose a machine learning approach that is based on statistical features of communication flow between two end-points. The statistical features are then used to develop and test a Parallel Neural Network Classifier Architecture (PNNCA), which is trained to recognize specific HTTP session patterns in a controlled environment, and then used to classify general traffic. The classifier’s performance and scalability measures have been compared with other neural network based approaches. The classifier’s correct classification rate (CCR) is calculated to be 96%.

The IRMA Community

Research IRM

A Scalable Approach to Network Traffic Classification for Computer Network Defense using Parallel Neural Network Classifier Architectures

Purchase

Abstract

Related Content

IRMA Sponsors