Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring

AI 中文解读

E-SpecFormer来了！这项研究给物联网设备装上了“无线信号雷达”，能在极低功耗下实时识别各种无线信号，性能却比现有边缘模型强出一大截。传统AI模型往往需要强大的计算资源，而这款新模型用了独创的LiTAN注意力机制，去掉了耗电的Softmax和层归一化操作，把参数压缩到不到一万个，速度却飙到了每帧仅92微秒。它就像个超级节能的“信号侦探”，不仅能区分正常通信和隐藏的恶意信号，还能根据设备算力自动切换大小版本。这意味着智能家居、工业传感器这类资源受限的设备，现在也能拥有专业级频谱监控能力。比如你家智能门锁能识别出异常干扰信号，防止黑客用特殊频率破解；或者公共WiFi能自动过滤隐蔽的攻击流量。更关键的是，这项技术开源且免费，开发者和企业可以轻松集成，成本比现有方案低一大截，未来普通消费者有望用上更安全、更可靠的物联网产品。

arXiv:2607.18285v1 Announce Type: new Abstract: We present E-SpecFormer (Edge Spectrum monitoring Transformer) for end-to-end automatic modulation and covert channel (CC) recognition. We introduce LiTAN (Linear Tanh Attention Network), a Softmax- and LayerNorm-free attention mechanism that reduces complexity while increasing accuracy in RF tasks. E-SpecFormer is parameterized in four scalable variants (Nano, Small, Medium, Large) to accommodate diverse hardware constraints. Using the RadioML2018 dataset for modulation recognition, the Nano variant achieves 86.5% average accuracy for Signal-to-Noise Ratios (SNRs)>0 dB, and on the hardware Trojan (HT)-based CC dataset it reaches 94.2% accuracy, both with fewer than 10k parameters and up to speed of 92 {\mu}s per frame on FPGA/CPU co-execution, surpassing state-of-the-art edge models at a fraction of their cost. These results establish E-SpecFormer as an edge-efficient solution for real-time spectrum intelligence on Internet of Things (IoT) devices. GitHub link to the repository: https://github.com/zsniko/E-SpecFormer.