论文标题
基于模糊的基于模糊的ID，用于检测无线网状IoT网络中的干扰攻击
Fuzzy-Logic Based IDS for Detecting Jamming Attacks in Wireless Mesh IoT Networks
论文作者
论文摘要
储层计算是预测湍流的有力工具，其简单的架构具有处理大型系统的计算效率。然而，其实现通常需要完整的状态向量测量和系统非线性知识。我们使用非线性投影函数将系统测量扩展到高维空间，然后将其输入到储层中以获得预测。我们展示了这种储层计算网络在时空混沌系统上的应用，该系统模拟了湍流的若干特征。我们表明，使用径向基函数作为非线性投影器，即使只有部分观测并且不知道控制方程，也能稳健地捕捉复杂的系统非线性。最后，我们表明，当测量稀疏、不完整且带有噪声，甚至控制方程变得不准确时，我们的网络仍然可以产生相当准确的预测，从而为实际湍流系统的无模型预测铺平了道路。
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.
