Graph Neural Networks for Jamming Source Localization

2025-06-01

AI Summary

To address the challenges of interference source localization in wireless networks—particularly poor robustness under sparse or ambiguous signals and difficulty in identifying interference sources—this paper formulates the task as an inductive graph regression problem for the first time and proposes a graph neural network (GNN)-based localization framework. Methodologically, it constructs a signal-space graph structure, incorporates dynamic attention mechanisms and multi-scale signal aggregation, and designs a confidence-guided estimation module that adaptively fuses data-driven predictions with domain-specific priors to ensure spatial consistency. Key contributions include: (i) the first inductive graph regression paradigm tailored for interference localization; and (ii) structured node representation learning coupled with a dynamic confidence-weighting mechanism. Experiments demonstrate over 40% reduction in localization error under low-sampling-density and high-interference conditions, significantly outperforming conventional geometric optimization methods. The code is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Graph-based learning has emerged as a transformative approach for modeling complex relationships across diverse domains, yet its potential in wireless security remains largely unexplored. In this work, we introduce the first application of graph-based learning for jamming source localization, addressing the imminent threat of jamming attacks in wireless networks. Unlike geometric optimization techniques that struggle under environmental uncertainties and dense interference, we reformulate localization as an inductive graph regression task. Our approach integrates structured node representations that encode local and global signal aggregation, ensuring spatial coherence and adaptive signal fusion. To enhance robustness, we incorporate an attention-based graph neural network that adaptively refines neighborhood influence and introduces a confidence-guided estimation mechanism that dynamically balances learned predictions with domain-informed priors. We evaluate our approach under complex radio frequency environments with varying sampling densities and signal propagation conditions, conducting comprehensive ablation studies on graph construction, feature selection, and pooling strategies. Results demonstrate that our novel graph-based learning framework significantly outperforms established localization baselines, particularly in challenging scenarios with sparse and obfuscated signal information. Code is available at [https://github.com/daniaherzalla/gnn-jamming-source-localization](https://github.com/daniaherzalla/gnn-jamming-source-localization).

Problem

• Localizing jamming sources in wireless networks using graph learning
• Overcoming environmental uncertainties in jamming source localization
• Enhancing robustness with attention-based graph neural networks

Innovation

• Graph-based learning for jamming source localization
• Attention-based GNN refines neighborhood influence
• Confidence-guided mechanism balances predictions and priors