【论文阅读】Using Deep Learning to Eavesdrop on HDMI from its Unintended Electromagnetic Emanations（2024）

Deep-TEMPEST: Using Deep Learning to Eavesdrop on HDMI from its Unintended Electromagnetic Emanations（2024）

摘要

In this work, we address（解决） the problem of eavesdropping on digital video displays by analyzing the electromagnetic waves（电磁波） that unintentionally emanate from the cables（电缆） and connectors（连接器）, particularly HDMI. This problem is known as TEMPEST. Compared to the analog（模拟） case (VGA), the digital case is harder due to a 10-bit encoding that results in a much larger bandwidth（更大的带宽） and non-linear mapping（非线性映射） between the observed signal（观察信号） and the pixel’s intensity（像素强度）. As a result（因此）, eavesdropping systems designed for the analog case obtain unclear and difficult-to-read images when applied to digital video. The proposed solution is to recast the problem as an inverse problem（逆问题） and train a deep learning module to map the observed electromagnetic signal（电磁信号） back to the displayed image. However, this approach still requires a detailed mathematical analysis（详细的数学分析） of the signal, firstly to determine the frequency at which to tune but also to produce training samples without actually needing a real TEMPEST setup. This saves time and avoids the need to obtain these samples, especially if several configurations（配置） are being considered. Our focus is on improving the average Character Error Rate（平均字符错误率） in text, and our system improves this rate by over 60 percentage points compared to previous available implementations. The proposed system is based on widely available Software Defined Radio and is fully open-source, seamlessly integrated into the popular GNU Radio framework. We also share the dataset we generated for training, which comprises both simulated and over 1000 real captures. Finally（最后）, we discuss some countermeasures to minimize the potential risk of being eavesdropped by systems designed based on similar principles（原则）.

论文链接

Deep-TEMPEST: Using Deep Learning to Eavesdrop on HDMI from its Unintended Electromagnetic Emanations