One Cross-Layer Anomaly Intrusion Detection System Model for Wireless Ad Hoc Networks

A novel cross-layer anomaly intrusion detection system model for wireless Ad hoc networks was proposed.The model uses naive Bayesian classification algorithm,Markov chain construction algorithm and association rule mining algorithm for anomaly detection in MAC layer,routing layer,and application layer respectively.Local integration module takes the results from three anomaly detection subsystems,and average of weighted sum of them gives the output of the local integration.Global integration module integrates the neighbor node(s) result and calculates the final result for taking decision towards response module.The model and algorithem are tested by several kinds representative attacks.The experimental results show that the model has high detection rate,and which can deduce the false alarm rate effectively.