BlackoutADR: Exploiting adaptive data rate vulnerabilities in LoRaWAN-based FANETs

This paper introduces BlackoutADR , a novel adversarial attack exploiting LoRaWAN’s Adaptive Data Rate (ADR) mechanism in cellular-connected UAV networks, with applicability to other IoT systems as well. By subtly manipulating Received Signal Strength Indicator (RSSI) and Signal-to-Noise Ratio (SNR), BlackoutADR increases UAV transmission power, causing 45% faster battery depletion within 100 s of simulation time and disrupting network operations. Using NS-3 simulations with a 20-UAV FANET, we evaluate its evasion of multiple ML-based IDSs (CNN, LSTM, BiLSTM, FNN, LoRaWAN-specific). Results show BlackoutADR remains undetected due to its subtle manipulations evading even dynamic thresholds, outperforming traditional jamming attacks. To address the identified vulnerability, we outline reactive measures, including dynamic threshold-based IDSs, secure ADR mechanisms, and recommendations for drone manufacturers.