Learning a Switching Bayesian Model for Jammer Detection in the Cognitive-Radio-Based Internet of Things
Muhammad Hashier Muneeb Farrukh, Ali Krayani, Mohamad Baydoun, Lucio Marcenaro, Yue Gao, Carlo S. Regazzoni · 2019
The proliferation of interconnected objects in the Internet of Things (IoT) can be benefit from integration of cognitive radio (CR) technologies at the network level. IoT networks equipped with cognitive capabilities can help to effectively alleviate the problem of spectrum scarcity. However, the IoT network can suffer from jammer attacks that interfere with user transmissions and disrupt communications. In this paper, we consider a CR-IoT network based on Orthogonal Frequency Division Multiplexing (OFDM) modulation scheme and a reactive jammer is hypothesized to be present in the network. A jammer detection method is proposed that is based on learning a switching Dynamic Bayesian Network (DBN) from normal OFDM data transmissions that is capable to detect abnormal situations. The proposed model is shown to be capable to detect and locate multiple jammers. The comparison with a conventional energy detection shows the validity of the proposed approach.