发表机构
Fraunhofer Institute for Integrated Circuits IIS; Friedrich-Alexander University (FAU) Erlangen-Nürnberg; University of Navarra; Tampere University; University of Applied Sciences Erlangen-Nuremberg（弗劳恩霍夫集成电路研究所; 弗里德里希·亚历山大大学; 纳瓦拉大学; 坦佩雷大学; 埃尔朗根-纽伦堡应用科学大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对低成本GNSS干扰器的威胁，构建2025年挪威Jammertest的多源干扰真实数据集，测试17种ML架构并迁移YOLOv8s等检测器，发现区域内分类准确率近99%但跨区域性能骤降，凸显域偏移鲁棒性的必要性。
AI 中文摘要
来自低成本GNSS干扰器的有意射频干扰日益威胁基于卫星的定位的准确性和可靠性。缓解这一威胁不仅需要检测，还需要稳健的波形分类与表征、用于定位的到达方向推断，以及现实工作条件下对接收机性能的影响评估；所有这些都面临着设备、传感器、环境和卫星几何结构间强烈分布偏移的挑战。我们通过整理2025年挪威安多亚Jammertest期间记录的专用真实世界数据集来应对这些挑战，该数据集覆盖两个室外测试区域，同时采集了单天线E1/E5接收机模块和2x2 CRPA阵列的测量数据。该数据集涵盖多种干扰、欺骗和重放场景，包括连续波（CW）、伪随机噪声（PRN）、扫频/线性调频（chirp）以及多发射器配置，还辅以每条记录的元数据，支持时间对齐的地面真值。在方法上，我们对17种机器学习（ML）架构进行干扰调制识别和多任务表征（类型、占用带宽和信号强度）的基准测试，并通过接收机感知的频谱分离系数（SSC）量化与导航相关的性能下降，该系数将测量的频谱映射到有效载噪比（C_s/N_0）损耗。为实现多源分析，我们将在标注频谱图数据集上预训练的YOLOv8s和RF-DETR检测器迁移，以在GNSS频谱图中定位多个同时出现的干扰源，随后对每个检测到的分量进行表征。结果显示，区域内分类准确率接近99%，但跨区域性能大幅下降，凸显了对现实域偏移的鲁棒性需求。
英文摘要
Intentional radio-frequency interference from low-cost GNSS jammers increasingly threatens the accuracy and reliability of satellite-based positioning. Mitigating this threat requires not only detection but also robust waveform classification and characterization, direction-of-arrival inference for localization, and impact estimation on receiver performance under realistic operating conditions; all of which are challenged by strong distribution shifts across devices, sensors, environments, and satellite geometries. We address these challenges by compiling a dedicated real-world dataset recorded during Jammertest 2025 (Andoya, Norway), covering two outdoor test areas with parallel measurements from a single-antenna E1/E5 receiver module and a 2x2 CRPA-array. The dataset spans diverse jamming, spoofing, and meaconing scenarios, including CW, PRN, sweep/chirp, and multi-emitter configurations, and is complemented by per-recording metadata enabling time-aligned ground truth. Methodologically, we benchmark 17 machine learning (ML) architectures for interference-modulation recognition and multi-task characterization (type, occupied bandwidth, and signal strength), and we quantify navigation-relevant degradation via a receiver-aware spectral separation coefficient (SSC) that maps measured spectra to effective (C_s/N_0)_{eff} loss. To enable multi-source analysis, we transfer a YOLOv8s and RF-DETR detector pretrained on a labeled spectrogram dataset to localize multiple simultaneous interferers in GNSS spectrograms and subsequently characterize each detected component. Results show near-99% within-area classification accuracy but substantial cross-area performance drops, highlighting the need for robustness to real-world domain shifts.
Comments15 pages, 14 figures
Journal refPending publication at ION GNSS+ 2026
