Anomaly Detection in Wireless Mobile Ad Hoc Networks With Multi-Layer Observation Sequences

Free registration required

Executive Summary

Mobile ad hoc Networks (MaNet) are very vulnerable to malicious attacks due to the nature of mobile computing environment such as absence of fixed infrastructures, wireless communication channels, limited power and bandwidth, dynamically changing and distributed network topology, etc. The general existing Intrusion Detection Systems (IDS) have provided little evidence that they are applicable to a broader range threats. Based on the generalized and cooperative intrusion detection architecture, the authors present an anomaly detection mechanism aiming at multiple malicious attacks by monitoring multi-layer activities, which is independent with a particular routing protocol. By collecting multi-layer observation sequences, Hidden Semi-Markov Model (HSMM) is explored to describe the network behaviors of legitimate nodes and to implement the anomaly detection for various existing and unknown malicious attacks.

  • Format: PDF
  • Size: 209.4 KB