Deep Neural Network Security From a Hardware Perspective
Deep Neural Network Security From a Hardware Perspective
复制标题
从硬件角度看深度神经网络安全
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Xiaolin Xu
中科院分区：
文献类型：
--
作者：
Tong Zhou;Yuheng Zhang;Shijin Duan;Yukui Luo;Xiaolin Xu
深度神经网络（DNN）已被部署在各种计算平台上用于加速，使得DNN的硬件安全性成为一个新的问题。介绍了几种与DNN硬件加速器相关的攻击方法，这些方法要么影响DNN的推理精度，要么泄露DNN的结构和参数的隐私。为了对这一新兴研究领域有一个全面的了解，在本次调查中，我们从硬件的角度系统地回顾了DNN安全的最新研究进展。特别讨论了现有针对不同DNN加速平台的面向硬件的攻击，并指出了潜在的漏洞。
Deep neural networks (DNNs) have been deployed on various computing platforms for acceleration, making the hardware security of DNNs an emerging concern. Several attacking methods related to the hardware accelerator of DNN have been introduced, which either affect the DNN inference accuracy or leak the privacy of DNN architectures and parameters. To provide a generic understanding of this emerging research area, in this survey, we systematically review the recent research progress of DNN security from a hardware perspective. Specially, we discuss the existing hardware-oriented attacks targeting different DNN acceleration platforms, and point out the potential vulnerabilities.