Performance adaptation in real-time intrusion detection systems

  • Authors:
  • Wenke Lee;João B. D. Cabrera;Ashley Thomas;Niranjan Balwalli;Sunmeet Saluja;Yi Zhang

  • Affiliations:
  • College of Computing, Georgia Institute of Technology, Atlanta, GA;Scientific Systems Company Inc., Woburn, MA;Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC;College of Computing, Georgia Institute of Technology, Atlanta, GA;College of Computing, Georgia Institute of Technology, Atlanta, GA;College of Computing, Georgia Institute of Technology, Atlanta, GA

  • Venue:
  • RAID'02 Proceedings of the 5th international conference on Recent advances in intrusion detection
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

A real-time intrusion detection system (IDS) has several performance objectives: good detection coverage, economy in resource usage, resilience to stress, and resistance to attacks upon itself. In this paper, we argue that these objectives are trade-offs that must be considered not only in IDS design and implementation, but also in deployment and in an adaptive manner. We show that IDS performance trade-offs can be studied as classical optimization problems. We describe an IDS architecture with multiple dynamically configured front-end and back-end detection modules and a monitor. The IDS run-time performance is measured periodically, and detection strategies and workload are configured among the detection modules according to resource constraints and cost-benefit analysis. The back-end performs scenario (or trend) analysis to recognize on-going attack sequences, so that the predictions of the likely forthcoming attacks can be used to pro-actively and optimally configure the IDS.