Generating realistic workloads for network intrusion detection systems

  • Authors:
  • Spyros Antonatos;Kostas G. Anagnostakis;Evangelos P. Markatos

  • Affiliations:
  • Institute of Computer Science Foundation for Research & Technology - Hellas;Univ. of Pennsylvania;Institute of Computer Science Foundation for Research & Technology - Hellas

  • Venue:
  • WOSP '04 Proceedings of the 4th international workshop on Software and performance
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

While the use of network intrusion detection systems (nIDS) is becoming pervasive, evaluating nIDS performance has been found to be challenging. The goal of this study is to determine how to generate realistic workloads for nIDS performance evaluation. We develop a workload model that appears to provide reasonably accurate estimates compared to real workloads. The model attempts to emulate a traffic mix of different applications, reflecting characteristics of each application and the way these interact with the system. We have implemented this model as part of a traffic generator that can be extended and tuned to reflect the needs of different scenarios. We also present an approach to measuring the capacity of a nIDS that does not require the setup of a full network testbed.