The multi-million dollar investment required for modern machine learning (ML) has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA Cores in a GPU. For the first time, our work demonstrates parameter extraction on the specialized GPU's Tensor Core units, most commonly used GPU units nowadays due to their superior performance, via near-field physical side-channel attacks. Previous work targeted only the general-purpose CUDA Cores in the GPU, the functional units that have been part of the GPU since its inception. Our method is tailored to the GPU architecture to accurately estimate energy consumption and derive efficient attacks via Correlation Power Analysis (CPA). Furthermore, we provide an exploratory analysis of hyperparameter and weight leakage from LLMs in far field and demonstrate that the GPU's electromagnetic radiation leaks even 100\,cm away through a glass obstacle.

翻译：现代机器学习所需的数百万美元投资使得大型机器学习模型成为窃取的主要目标。作为回应，模型窃取领域应运而生。基于物理侧信道信息的攻击已证明，即使在GPU的CUDA核心上，深度神经网络模型提取也是可行的。我们的工作首次通过近场物理侧信道攻击，在专用GPU的张量核心单元上实现了参数提取——由于卓越的性能，这些单元已成为当今最常用的GPU组件。先前的研究仅针对GPU中的通用CUDA核心（自GPU诞生以来就存在的功能单元）。我们的方法针对GPU架构进行定制，以精确估计能耗并通过相关功耗分析（CPA）实现高效攻击。此外，我们对远场条件下大型语言模型的超参数与权重泄露进行了探索性分析，并证明GPU的电磁辐射甚至能穿透玻璃障碍物在100厘米外发生泄露。