AI 中文总结
研究通过智能手机加速度计进行声学窃听，提出LEAKFORGE框架，将其转换为物理引导的数据生成问题，通过采样音频到加速度计传递函数族合成多样轨迹，训练模型可应用于新智能手机轨迹。
AI 中文摘要
我们提出了LEAKFORGE，这是一个与设备无关的框架，它将跨设备加速度计窃听转换为物理引导的数据生成问题。关键在于，特定设备的泄漏并非任意的，其主要变化存在于音频到加速度计传递函数的受限族中。LEAKFORGE对该族进行采样，从普通语音中合成大规模、设备多样的加速度计轨迹，明确建模机电传递、结构共振、滤波和混叠。在这个合成域中完全训练的窃听模型随后可直接应用于来自以前未见过的智能手机的轨迹。
英文摘要
We present LEAKFORGE, a device-agnostic framework that converts cross-device accelerometer eavesdropping into a physics-guided data-generation problem. Crucially, device-specific leakage is not arbitrary; its dominant variation lies within a constrained family of audio-to-accelerometer transfer functions. LEAKFORGE samples this family to synthesize large-scale, device-diverse accelerometer traces from ordinary speech, explicitly modeling electromechanical transfer, structural resonances, filtering, and aliasing. An eavesdropping model trained entirely in this synthetic domain can then be applied directly to traces from previously unseen smartphones.
CommentsThis manuscript has been withdrawn pending resolution of an authorship attribution dispute. A revised version may be submitted after the matter is resolved
