A Machine Learning Attacks Resistant Two Stage Physical Unclonable Functions Design
A Machine Learning Attacks Resistant Two Stage Physical Unclonable Functions Design
复制标题
一种抗机器学习攻击的两阶段物理不可克隆函数设计
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Basel Halak
中科院分区：
文献类型：
--
作者：
Haibo Su;Mark Zwolinski;Basel Halak
物理不可克隆功能（puf）已被设计用于许多安全应用，如识别、设备认证和密钥生成，特别是用于轻型电子产品。增强安全性的传统方法（如散列函数）可能代价高昂且依赖于资源。然而，使用机器学习（ML）建模攻击显示了大多数puf的脆弱性。在本文中，提出了一种32位电流镜和16位仲裁puf在65nm CMOS技术中的组合，以提高对建模攻击的弹性。两个puf都容易受到机器学习攻击，我们将输出预测率从99.2%和98.8%分别降低到60%。
Physical Unclonable Functions (PUFs) have been designed for many security applications such as identification, authentication of devices and key generation, especially for lightweight electronics. Traditional approaches to enhancing security, such as hash functions, may be expensive and resource dependent. However, modelling attacks using machine learning (ML) show the vulnerability of most PUFs. In this paper, a combination of a 32-bit current mirror and 16-bit arbiter PUFs in 65nm CMOS technology is proposed to improve resilience against modelling attacks. Both PUFs are vulnerable to machine learning attacks and we reduce the output prediction rate from 99.2% and 98.8% individually, to 60%.