UAV Fleet Intrusion Detection and Fault Diagnosis for ITS Operations

Abstract

UAV fleets are increasingly deployed as aerial sensing and communication nodes that support intelligent transportation systems operations, including traffic monitoring, infrastructure inspection, and incident response. However, cyber intrusions in air–ground communication and physical faults in onboard subsystems can jointly disrupt data timeliness and service continuity, undermining operational reliability. This paper presents an integrated deep learning framework that jointly performs intrusion detection and fault diagnosis from multi-source network-traffic and flight-telemetry features. A task-aware static feature partitioning strategy decouples network and physical domain representations to mitigate cross-task interference while retaining shared learning. Experiments on a combined multi-source dataset show that the proposed method achieves 96.11% accuracy for intrusion detection and 97.49% accuracy for fault diagnosis, outperforming representative machine-learning and deep-learning baselines. Lightweight profiling further indicates the suitability of the proposed framework for real-time onboard or edge deployment, with an average inference time of 0.23 milliseconds per sample and 0.38 megabytes of parameters.