BGPAD tool

Introduction

BGPAD, is an implantation to various machine learning algorithms to detect BGP anomalies such as Slammer, Nimda, Code Red I. The implementation relays on GUIDE and STATISTICAL MATLAB toolboxes.
BGPAD Tool was tested on Windows 7 using Matlab 2013a.

Running BGPAD tool

Download BGPAD Tool (120,017 Kbytes zip file. Note: Use only Feature Exploration and Naive Bayes (NB) options.)
Download BGPAD Tool (revised) (119,402 Kbytes zip file. Note: Use only Navie Bayes (NB) and Hidden Markov Model (HMM) options.)
The BGPAD_tool package includes a README file with instructions on how to run the tool.

Related publications

Nabil Al-Rousan's M.A.Sc. thesis: N. Al-Rousan, "Comparison of machine learning models for classification of BGP anomalies," Aug. 2012.

N. Al-Rousan, S. Haeri, and Lj. Trajkovic, "Feature selection for classification of BGP anomalies using Bayesian models," in Proc. ICMLC 2012, Xi'an, China, July 2012, pp. 140-147.

N. Al-Rousan and Lj. Trajkovic, "Machine learning models for classification of BGP anomalies," in Proc. IEEE Conference on High Performance Switching and Routing, HPSR 2012, Belgrade, Serbia, June 2012, pp. 103-108.

Y. Li, H. J. Xing, Q. Hua, X.-Z. Wang, P. Batta, S. Haeri, and Lj. Trajkovic, "Classification of BGP anomalies using decision trees and fuzzy rough sets," in Proc. IEEE International Conference on Systems, Man, and Cybernetics (SMC 2014), San Diego, CA, October 2014, pp. 1331-1336.

Questions

If you have any questions related to the BGPAD tool, please contact Ljiljana Trajkovic ljilja at sfu.ca.
Created by: Nabil Al-Rousan <rousani@gmail.com>.
Posted by: Prerna Batta <pbatta@sfu.ca>.

Mon Sep 28 17:57:43 PDT 2015