CT PUF: Configurable Tristate PUF Against Machine Learning Attacks for IoT Security
| Autor: | Jiliang Zhang, Wanli Chang, Zhiyang Guo, Chaoqun Shen, Qiang Wu |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Authentication
Hardware security module Computer Networks and Communications Computer science business.industry Physical unclonable function Arbiter Machine learning computer.software_genre Computer Science Applications ComputingMilieux_MANAGEMENTOFCOMPUTINGANDINFORMATIONSYSTEMS Hardware and Architecture Authentication protocol Signal Processing Overhead (computing) Artificial intelligence Field-programmable gate array business Bitwise operation computer Information Systems |
| Zdroj: | IEEE Internet of Things Journal. 9:14452-14462 |
| ISSN: | 2372-2541 |
| DOI: | 10.1109/jiot.2021.3090475 |
| Popis: | Physical unclonable function (PUF) is a promising lightweight hardware security primitive for resource-limited Internet-of-Things (IoT) devices. Strong PUFs are suitable for lightweight device authentication because it can generate quantities of challenge-response pairs. Unfortunately, while the machine learning (ML) techniques have benefited various areas such as Internet, industrial automation, robotics and gaming, they pose a severe threat to PUFs by easily modelling their behaviour. This paper first shows that even a recently reported dual-mode PUF can be cloned by ML (prediction accuracy of up to 95%). To solve this issue, we propose a configurable tristate (CT) PUF which can flexibly perform as an arbiter PUF, a ring oscillator (RO) PUF, or a bistable ring (BR) PUF with a bitwise XOR-based mechanism to obfuscate the relationship between the challenge and the response, hence resisting the ML attacks. An authentication protocol for the use in IoT security is presented. The CT PUF is implemented on Xilinx ZedBoard FPGAs with placement and routing details described. The experimental results show that the modelling accuracy of logistic regression (LR), support vector machines (SVM), covariance matrix adaptation evolutionary strategies (CMA-ES), and artificial neural networks (ANN) is close to 60% (50% as the ideal number in theory) while meeting the PUF requirements for uniformity, reliability, and uniqueness. The hardware overhead and power consumption are slight. The entire project has been open-sourced. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|