MULTI-LEVEL NETWORK RESILIENCE: TRAFFIC ANALYSIS, ANOMALY DETECTION AND SIMULATION

Abstract
Traffic analysis and anomaly detection have been extensively used to characterize network utilization as well as to identify abnormal network traffic such as malicious attacks. However, so far, techniques for traffic analysis and anomaly detection have been carried out independently, relying on mechanisms and algorithms either in edge or in core networks alone. In this paper we propose the notion of multi-level network resilience, in order to provide a more buy pill robust traffic analysis and anomaly detection architecture, combining mechanisms and algorithms operating in a coordinated fashion both in the edge and in the core networks. This work is motivated by the potential complementarities between the research being developed at IIT Madras and Lancaster University. In this paper we describe the current work being developed at IIT Madras and Lancaster on traffic analysis and anomaly detection, and outline the principles of a multi-level resilience architecture.

Authors
Angelos Marnerides1, Cyriac James2, Alberto Schaeffer-Filho3, Saad Yunus Sait4, Andreas Mauthe5 and Hema Murthy6
1,3,5Lancaster University, United Kingdom,2,4,6Indian Institute of Technology Madras, India

Keywords
Traffic Analysis, Core and Edge Networks, Network Resilience, Anomaly Detection
Published By :
ICTACT
Published In :
ICTACT Journal on Communication Technology
( Volume: 2 , Issue: 2 )
Date of Publication :
June 2011

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.