DroneShield-AI：一种用于受争议空域中实时自主无人机威胁检测、行为意图分类和群体智能的多模态传感器融合框架
DroneShield-AI: A Multi-Modal Sensor Fusion Framework for Real-Time Autonomous Drone Threat Detection, Behavioral Intent Classification, and Swarm Intelligence in Contested Airspace
AI总结：
提出DroneShield-AI框架，集成RF信号分类、声学检测、YOLOv8视觉检测等六层处理，通过行为意图分类引擎（BICE）实现六类威胁分类并提前30秒预警，以及图神经网络群体智能模块（GNN-SIM）分析多无人机编队，在低成本硬件上达到96.1%检测精度和142ms延迟。
摘要：
无人机（UAV）威胁已成为21世纪定义性的安全挑战。本文提出DroneShield-AI，一个统一的开放框架，集成了六个处理层：RF信号分类、声学电机特征检测、基于YOLOv8的视觉检测、证据加权传感器融合、行为意图分类引擎（BICE）和图神经网络群体智能模块（GNN-SIM）。BICE首次引入了针对无人机飞行模式的系统性六类威胁分类法，能够提前30秒发出预测性操作员警报。GNN-SIM是首个用于对抗性多无人机编队分析的开放框架，采用图注意力网络。在三个公开的真实世界数据集上评估，融合流水线在约500-780美元总系统成本的商用CPU级硬件上实现了96.1%的检测准确率、3.2%的误报率、AUC-ROC：0.981以及142ms的端到端延迟。所有代码、模型权重和仿真数据集在提交时公开发布。
英文摘要：
Unmanned Aerial Vehicle (UAV) threats have emerged as a defining security challenge of the 21st century. This paper presents DroneShield-AI, a unified open framework integrating six processing layers: RF signal classification, acoustic motor-signature detection, YOLOv8-based visual detection, evidence-weighted sensor fusion, a Behavioral Intent Classification Engine (BICE), and a Graph Neural Network Swarm Intelligence Module (GNN-SIM). This v2 revision reports measured results on the completed implementation (495 automated tests), superseding the v1 simulation-only preprint. On real public data: RF presence detection reaches F1 0.9924; acoustic detection reaches 98.12% accuracy, though a 4-feature statistical baseline reaches 93.25% on the same split, so the model's drone-specific contribution is approximately 4.9 points, a property of dataset provenance rather than a leakage bug; visual detection (YOLOv8) reaches AP50 0.8782 on a held-out test split, from a model still improving when training stopped. No fused-accuracy figure is reportable, since the three real-data layers use independently collected, unsynchronized datasets with no shared ground truth. BICE and GNN-SIM remain evaluated on physics-calibrated simulation data pending real adversarial and swarm field data: BICE shows a consistent robustness advantage over a trivial baseline under distribution shift; GNN-SIM underperforms its own trivial baseline in-distribution but independently replicates BICE's noise-robustness advantage, regarded as this work's most durable finding. All code, trained checkpoints, and the full test suite are publicly released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
