[论文] Overcoming Data Scarcity and Confidentiality in Hardware Assurance via...

论文概要

研究领域: CV
作者: Gijung Lee, Ronald Wilson, Damon L. Woodard
发布时间: 2026-08-12
arXiv: 2508.05150

中文摘要

硬件验证依赖扫描电子显微镜（SEM）来验证纳米级结构，但组装自动化分析所需的大规模高质量数据集受到耗时采集和专有设计严格知识产权（IP）限制的双重阻碍。本文提出一种隐私保护流程，通过对功能设计进行重度扭曲来确保IP安全，同时从少量初始样本生成视觉上逼真的合成数据集。首先，StyleGAN学习硬件布局掩码的分布，生成新颖的、宏观上多样化的结构。随后，条件GAN（Pix2PixHD）将这些掩码转换为逼真的SEM图像，保留真实的纹理和噪声。本工作的主要发现是：仅在此合成数据上训练的分割模型不仅成功实现了向真实图像的'sim-to-real'迁移，还优于在有限真实数据集上训练的基线模型。由于底层合成布局明显是新颖的，且不复制原始设计的任何特定专有布线，部署最终分割模型可以有效降低将敏感IP暴露给梯度反转和成员推断等攻击的风险，为硬件验证提供了高度安全、高性能的解决方案。

原文摘要

Hardware assurance relies on scanning electron microscopy (SEM) to verify nanoscale structures, but assembling the large, high-quality datasets required for automated analysis is impeded by time-intensive acquisition and strict intellectual property (IP) constraints on proprietary designs. We propose a privacy-preserving pipeline that secures IP by heavily distorting the functional design while generating a visually realistic synthetic dataset from a small set of initial examples. A StyleGAN first learns the distribution of hardware layout masks to generate novel, macroscopically varied structures. Subsequently, a conditional GAN (Pix2PixHD) translates these masks into realistic SEM images that preserve authentic textures and noise. The primary finding of this work is that a segmentation m...

自动采集于 2026-08-12

#论文 #arXiv #CV #小凯