Fuzzy-Logic Based IDS for Detecting Jamming Attacks in Wireless Mesh IoT Networks

The investigation in this paper targets the design and the evaluation of jamming intrusion detection based on Fuzzy Logic in wireless mesh IoT Networks in a distributed manner. Our approach uses information collected at local nodes and from the sink as input to the fuzzy logic controller. In order to find the best set of inputs, distributed or centralized, we made a comparison between five different combinations of parameters. The investigation uses the values of the ETX, Retransmissions, Packets Drop per terminal (PDPT) and Packet Delivery Ratio (PDR) as inputs to a fuzzy inference system to get Jamming Index (JI) as the system's output. The proposed method was evaluated based on the following metrics: Accuracy, Precision, Specificity, False positive rate (FPR), Recall, False negative rate (FNR) and ROC curve. In order to evaluate this approach, we implement experiments in various scenarios using the Contiki OS and the Cooja simulator tool.