SPOC-Net improves recognition of combined GNSS jamming signals
SPOC-Net: Single-Primitive Online Composition Network for GNSS Jamming Set Recognition
Computer Vision and Pattern Recognition
Summary
Satellite navigation signals can be disrupted by jamming, which often involves mixing different types of interference. The authors propose SPOC-Net, a method that breaks down these mixed jamming signals into their basic parts to identify each one individually. Training SPOC-Net requires only simple recorded jamming signals, and it can recognize new mixtures it has never seen before. This approach achieved over 80% accuracy in identifying exact combinations and outperformed other methods significantly on unseen signal mixes.
What this means in practice
- •For gnss system operators: Enable more reliable detection and classification of combined jamming signals to maintain accurate positioning and navigation services.
- •For wireless security teams: Improve monitoring tools to identify and respond to complex interference patterns in radio communications.
Authors
Zhihan Zeng, Kaihe Wang, José A. López-Salcedo, Gonzalo Seco-Granados, Zhongpei Zhang
Abstract
Reliable positioning, navigation, and timing support intelligent transportation, autonomous systems, and space-air-ground integrated networks. However, global navigation satellite system (GNSS) jamming recognizers that treat each mixture as a separate class are difficult to extend to new combinations. Therefore, this paper proposes SPOC-Net, which decomposes the recognition problem into identifying a set of basic jamming components. Multi-resolution time-frequency features and learned component queries provide evidence for each component type. A high-resolution branch estimates the number of active types, and a structured decoder combines this estimate with component evidence to select a valid set. For training, measured single-component records are the only physical samples used in gradient optimization. Their associated clean in-phase and quadrature (IQ) sequences are combined on demand during training to produce labeled mixtures with different relative powers and jamming-to-noise ratios. Separate measured mixtures from ten training-listed compositions support model selection and decoder calibration; six other compositions are reserved for final testing. Evaluation on 14,220 independently generated, conductively combined, and recorded radio frequency mixtures yields 80.69% exact-set accuracy and a 92.84% micro-averaged F1 score. On combinations excluded from model development, SPOC-Net achieves 80.89% exact-set accuracy, exceeding the strongest comparison method by 18.77 percentage points under the reported protocols.