Privacy leakage of LoRaWAN smart parking occupancy sensors

Abstract

Development of smart cities is enabled by its core concepts of smart and sustainable mobility, where Low Power Wide Area Network (LPWAN) such as Long Range Wide Area Network (LoRaWAN) became one of the most important Internet of Things (IoT) technologies. Due to its low power consumption, simple setup, and large communication range, LoRaWAN smart parking devices are already employed to reduce congestion and improve quality of life. This paper studies privacy leakage of LoRaWAN smart parking communication devices. Namely, when a vehicle as a metallic obstacle obscures the LoRaWAN smart parking device, the signal strength will be significantly reduced on the receiver side. Consequently, the variation in the signal strength of LoRaWAN parking systems transmits information about parking space occupancy, allowing the implementation of a passive side-channel attack at large distances. Using supervised machine learning techniques based on Neural Network, the attacker can estimate parking lot occupancy with accuracy up to 97%, while Random Forrest approach reaches the accuracy over 98%.