Machine Learning and Hardware security: Challenges and Opportunities -Invited Talk-
Machine Learning and Hardware security: Challenges and Opportunities -Invited Talk-
复制标题
机器学习与硬件安全：挑战与机遇-特邀演讲-
DOI：
10.1145/3400302.3416260
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ville Yli
中科院分区：
文献类型：
--
作者：
F. Regazzoni;S. Bhasin;Amir Alipour;Ihab Alshaer;Furkan Aydin;Aydin Aysu;V. Beroulle;G. D. Natale;P. Franzon;D. Hély;N. Homma;Akira Ito;Dirmanto Jap;Priyank Kashyap;I. Polian;S. Potluri;Rei Ueno;E. Vatajelu;Ville Yli
机器学习技术已大大改变了我们的生活。他们帮助改善了我们的日常习惯，但它们也证明是对更高级和复杂应用的极有用的工具。但是，在机器学习技术的大规模扩散下，硬件安全问题的含义仍然可以完全理解。本文首先要重点介绍机器学习在硬件安全性方面的新应用，例如评估量子加密硬件的评估以及从神经网络中进行物理上无倾斜功能的提取。后来，证明了基于电磁侧通道测量值的实用模型提取攻击，之后是对通过水印来保护专有模型的策略的讨论。
Machine learning techniques have significantly changed our lives. They helped improving our everyday routines, but they also demonstrated to be an extremely helpful tool for more advanced and complex applications. However, the implications of hardware security problems under a massive diffusion of machine learning techniques are still to be completely understood. This paper first highlights novel applications of machine learning for hardware security, such as evaluation of post quantum cryptography hardware and extraction of physically unclonable functions from neural networks. Later, practical model extraction attack based on electromagnetic side-channel measurements are demonstrated followed by a discussion of strategies to protect proprietary models by watermarking them.