Routing anomaly detection in mobile ad hoc networks
Authors:
- B. SunBSB. Sun
- K. WuKWK. Wu
- U.W. PoochUPU.W. Pooch
- 3 June 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 25-31
Abstract
Intrusion detection systems (IDSs) for mobile ad hoc networks (MANETs) are necessary when we deploy MANETs in reality. In this paper, focusing on the protection of MANET routing protocols, we present a new intrusion detection agent model and utilize a Markov chain based anomaly detection algorithm to construct the local detection engine. The details of feature selection, data collection, data preprocess, Markov chain construction, classifier construction and parameter tuning are provided. Based on the routing disruption attack aimed at the dynamic source routing protocol (DSR), we study the performance of the algorithm at different mobility levels. Simulation results show that our algorithm can achieve low false positive ratio, high detection ratio, and small MTFA (mean time to the first alarm), especially when the mobility is low. Detailed analysis of simulation results is also presented.Keywords
This publication has 7 references indexed in Scilit:
- Markov chains, classifiers, and intrusion detection2005
- Detecting intrusions using system calls: alternative data models2003
- GloMoSim: a library for parallel simulation of large-scale wireless networks2002
- Mitigating routing misbehavior in mobile ad hoc networks2000
- Intrusion detection in wireless ad-hoc networks2000
- A revised taxonomy for intrusion-detection systemsAnnals of Telecommunications, 2000
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980