RF Fingerprinting of LoRa Transmitters Using Machine Learning with Self-Organizing Maps for Cyber Intrusion Detection
RF Fingerprinting of LoRa Transmitters Using Machine Learning with Self-Organizing Maps for Cyber Intrusion Detection
复制标题
DOI：
10.1109/ims37962.2022.9865441
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Manish Nair;Tommaso A. Cappello;Shuping Dang;Vaia Kalokidou;M. Beach
中科院分区：
文献类型：
--
作者：
Manish Nair;Tommaso A. Cappello;Shuping Dang;Vaia Kalokidou;M. Beach
本文提出了一种新的无监督机器学习（ML）算法，用于LoRa调制啁啾的快速RF指纹识别。仅基于接收信号强度指示器（RSSI）的识别不太可能在关键基础设施部署中产生用于传感器认证的稳健手段。在这里，使用无监督ML算法来快速训练人工神经网络（ANN）矩阵，为每个真实的发射机和潜在的流氓节点创建自组织映射（SOM）。可以在SOM上训练通用分类器，以将每个发射机精确地剖析为真实的或恶意的。通过实验验证，该方法在识别每个发射机（无论是真实的还是流氓节点）方面都取得了百分之一百的成功。
In this paper, a novel unsupervised machine learning (ML) algorithm is presented for the expeditious RF fingerprinting of LoRa modulated chirps. Identification based on received signal strength indicator (RSSI) alone is unlikely to yield a robust means for sensor authentication within critical infrastructure deployment. Here, an unsupervised ML algorithm is used to rapidly train an artificial neural network (ANN) matrix creating self-organizing maps (SOMs) for each authentic transmitter and a potential rogue node. A general classifier can be trained on the SOMs for precisely profiling each transmitter as either genuine or rogue. By means of experimental validation, this methodology demonstrated cent-percent success in recognizing each transmitter, either being a real or a rogue node.