Early Detection of Battery Depletion Attack in 5G-based UAV Networks

5G introduces various innovations and opportunities across network infrastructures. In 5G, Unmanned Aerial Vehicles (UAVs) can function as relays, and flying base stations to enhance communication availability and meet user demands across a wide range of applications. However, these advancements also bring security threats and malicious activities aimed at disrupting the communication system. One such threat is the Depletion of Battery (DoB) attack. Battery life is a critical component for UAVs, and attackers may attempt to deplete it in various ways, either through physical contact or remotely. Remote attacks can occur via GPS data channels or control channels, with the latter being particularly dangerous. In this work, we focus on an attack using Packet Forwarding Control Protocol (PFCP) messages. These messages are of high priority, requiring immediate attention from the UAV, which attackers exploit to drain the battery by sending numerous unauthorized PFCP messages. To address this attack, we have implemented the CUMSUM method for detection, taking into account the attack vector as a combination of energy consumption, battery depletion, and time. To further enhance our detection approach, we have developed a dynamic threshold strategy to minimize the false positive rate, making our solution more robust and reliable.