DC-PUF: Machine learning-resistant PUF-based authentication protocol using dependency chain for resource-constraint IoT devices

Abstract

The Physical Unclonable Function (PUF) is a hardware block which exploits the inherent process variations introduced during manufacturing to assign a unique fingerprint for each physical entity. This feature enables a low-cost authentication mechanism for connected devices, which is easy to evaluate but hard to predict. In this paper, we develop a low-cost PUF-based authentication mechanism called DC-PUF for resource-constrained IoT devices which can resist against machine-learning attacks. A new strategy known as the dependency chain (DC) is employed by which the response in each clock is dependent not only on the current challenge but also on the previous responses. This mechanism which takes advantage of both randomization and dependency chain hardens the ability to clone or predict the PUF instance by obfuscating the correlation between challenge-response pairs. Moreover, we propose a CNN-based attack scenario by which the existing PUF structures cannot resist while yielding more than 95% of prediction accuracy. The experimental results signify that unlike the existing PUFs, more than 58% of prediction accuracy cannot be reached when a sophisticated CNN-based attack is conducted to the DC-PUF, even with a large data-set. Also, the False-Negative rate is about 1%, in average, for three-bit mismatches in the receiving response in the presence of channel variations, whereas the False-Positive rate remains zero. Moreover, the proposed DC-PUF incurs lower hardware complexity and reasonable reliability and randomness compared to the existing PUF structures.