Deep Learning Based RFF Identification for LoRa

Traditional authentication schemes are implemented on the MAC layer for the LoRaWAN network. Radio frequency fingerprint (RFF) is a physical layer feature, originated from hardware imperfection.

In this demonstration, we will present a CNN-based RFF identification for LoRa. This demo is created by Mr Junzhe Ge as part of this final year project. This work has won the second place of the RISE Student Competition on hardware & embedded systems security in 2021.


RFF identification is an emerging technology and it can be used for authentication of the Internet of Things with low power consumption. This demonstration uses Lopy4 to transmit LoRa signals and RTL-SDR for reception. The signal processing and CNN training have been implemented by Python.

System Overview


Signal Generation

Any board that can generate LoRa signal without higher layers will work, e.g., Lopy4, Fipy. This demonstration uses eight Lopy4 boards as example.

Signal Reception and Processing

Deep Learning






Programming language and packages

Demo Video

Click the image below to watch the video. Hearbeat Key Generation Demo


Please contact Dr. Junqing Zhang (junqing.zhang at if you require further information.