汪鹏君^1,,,
连佳娜^{1, 2},
陈博¹
1.温州大学电气与电子工程学院 温州 325035
2.温州大学计算机与人工智能学院 温州 325035
基金项目:国家重点研发计划项目(2018YFB2202100)，国家自然科学基金(62174121, 61904125)，温州市基础性科研项目(G20190006, G20210023)

详细信息

作者简介:汪鹏君：男，1966年生，教授，研究方向为集成电路设计、信息安全等技术及其相关理论
连佳娜：女，1996年生，硕士生，研究方向为物理不可克隆函数攻击与防御
陈博：男，1981年生，讲师，研究方向为密码芯片攻击和防御理论及其VLSI实现

通讯作者:汪鹏君　wangpengjun@wzu.edu.cn

中图分类号:TN918.2; TP309

计量

文章访问数:345
HTML全文浏览量:147
PDF下载量:44
被引次数:0

出版历程

收稿日期:2021-07-19
修回日期:2021-08-20
网络出版日期:2021-09-06
刊出日期:2021-09-16

Sequence Cipher Based Machine Learning-Attack Resistance Method for Strong-PUF

Pengjun WANG^1,,,
Jiana LIAN^{1, 2},
Bo CHEN¹
1. College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, China
2. College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
Funds:The National Key Research and Development Program of China (2018YFB2202100), The National Natural Science Foundation of China (62174121, 61904125), The Wenzhou Basic Scientific Research Projects (G20190006, G20210023)


摘要
摘要:物理不可克隆函数(Physical Unclonable Function, PUF)在信息安全领域具有极其重要的应用前景，然而也存在其自身安全受机器学习攻击等方面的不足。该文通过对PUF电路和密码算法的研究，提出一种基于序列密码的强PUF抗机器学习攻击方法。首先，通过构造滚动密钥生成器产生随机密钥，并与输入激励进行混淆；然后，将混淆后的激励通过串并转换电路作用于强PUF，产生输出响应；最后，利用Python软件仿真和FPGA硬件实现，并分析其安全性和统计特性。实验结果表明，当建模所用激励响应对(Challenge Response Pairs, CRPs)高达10⁶组时，基于逻辑回归、人工神经网络和支持向量机的攻击预测率接近50%的理想值。此外，该方法通用性强、硬件开销小，且不影响PUF的随机性、唯一性以及可靠性。
关键词:硬件安全/
强物理不可克隆函数/
序列密码/
机器学习
Abstract:Physical Unclonable Function (PUF) has extremely important application prospects to the field of information security, however, there are also shortcomings in its own security from machine learning attacks and other aspects. By studying PUF circuits and cryptographic algorithm, a method based on sequence cipher of strong-PUF is proposed to resist machine learning attacks. Firstly, the random key is generated by constructing a rolling key generator, which is obfuscated with the input challenge; Then the obfuscated challenge is applied to the strong-PUF through a series-parallel conversion circuit to generate the output response; Finally, Python software simulation and FPGA hardware implementation are used to analyze the safety and statistical properties. The experimental results show that the attack prediction rates based on logistic regression, artificial neural network and support vector machine are close to the ideal value of 50% when the CRPs used for modeling are up to 10⁶ groups. In addition, this method has high versatile, low hardware overhead and does not affect the randomness, uniqueness and reliability of PUF.
Key words:Hardware security/
Strong-Physical Unclonable Function (PUF)/
Sequence cipher/
Machine learning



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=1eaf8fb5-615f-4cc0-bf7b-216d36ee021a