一句话：提出针对稀疏加速器上剪枝 DNN 的侧信道模型窃取攻击，将基于片外访存量的攻击扩展到剪枝模型。
深度神经网络模型常作为专有资产部署在边缘设备上，攻击者若具备物理访问能力，可利用片外内存访问量等侧信道推断模型信息。已有工作通过将数据传输量与层几何结构相关联，成功从边缘设备窃取稠密 DNN。本文（HuffDuff）进一步面向剪枝后的 DNN 与稀疏加速器，研究稀疏化带来的新侧信道风险，目标是从低功耗稀疏加速器中窃取剪枝模型。标题表明攻击利用了剪枝/稀疏结构在访存行为上的特征；摘要未详述具体方法、实验平台与成功率，但将模型窃取威胁从稠密场景扩展到更现实、更高效的稀疏推理部署场景。
Deep learning models are a valuable “secret sauce” that confers a significant competitive advantage. Many models are never visible to the user and even publicly known state-of-the-art models are either completely proprietary or only accessible via access-controlled APIs. Increasingly, these models run directly on the edge, often using a low-power DNN accelerator. This makes models particularly vulnerable, as an attacker with physical access can exploit side channels like off-chip memory access volumes. Indeed, prior work has shown that this channel can be used to steal dense DNNs from edge devices by correlating data transfer volumes with layer geometry.