SigChord: Sniffing Wide Non-sparse Multiband Signals for Terrestrial and Non-terrestrial Wireless Networks

2025-04-09

AI Summary

To address the low-overhead physical-layer sensing requirement for wideband, non-sparse, multi-band signals in integrated space–ground networks, this work overcomes the Nyquist sampling barrier. Method: We propose a signal sniffing framework leveraging low-cost sub-Nyquist RF hardware, featuring a novel Transformer-driven deep-regular hybrid interleaving algorithm for broadband spectrum sensing and high-fidelity signal reconstruction under sub-Nyquist sampling. Furthermore, we pioneer the integration of cascaded Transformer-based protocol identification and decoding directly into the physical-layer processing pipeline, enabling end-to-end unencrypted signal parsing. Results: Experimental evaluation demonstrates >99% detection and decoding accuracy for 4G/5G and LEO satellite signals, with a 34% reduction in sampling rate—significantly outperforming state-of-the-art sub-sampling sensing approaches.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

While unencrypted information inspection in physical layer (e.g., open headers) can provide deep insights for optimizing wireless networks, the state-of-the-art (SOTA) methods heavily depend on full sampling rate (a.k.a Nyquist rate), and high-cost radios, due to terrestrial and non-terrestrial networks densely occupying multiple bands across large bandwidth (e.g., from 4G/5G at 0.4-7 GHz to LEO satellite at 4-40 GHz). To this end, we present SigChord, an efficient physical layer inspection system built on low-cost and sub-Nyquist sampling radios. We first design a deep and rule-based interleaving algorithm based on Transformer network to perform spectrum sensing and signal recovery under sub-Nyquist sampling rate, and second, cascade protocol identifier and decoder based on Transformer neural networks to help physical layer packets analysis. We implement SigChord using software-defined radio platforms, and extensively evaluate it on over-the-air terrestrial and non-terrestrial wireless signals. The experiments demonstrate that SigChord delivers over 99% accuracy in detecting and decoding, while still decreasing 34% sampling rate, compared with the SOTA approaches.

Problem

• Efficient inspection of wide non-sparse multiband signals
• Reducing dependency on high-cost Nyquist-rate sampling radios
• Accurate signal recovery and analysis under sub-Nyquist sampling

Innovation

• Sub-Nyquist sampling for efficient signal inspection
• Transformer-based spectrum sensing and recovery
• Low-cost SDR implementation for multi-band analysis