Set-Based Obfuscation for Strong PUFs Against Machine Learning Attacks

TLDR

Strong PUFs are promising for device authentication but are vulnerable to machine‑learning attacks, and existing defenses suffer high overhead, reduced reliability, and fail against advanced attacks. The authors propose Random Set‑based Obfuscation (RSO) to protect Strong PUFs from such attacks. RSO stores several stable PUF responses as a set, uses a true random number generator to XOR selected keys with challenges and responses, and updates the set when the attacker’s collected CRPs exceed a threshold. Experiments on a 64 × 64 Arbiter PUF with a set size of 32 show that even after 1 million CRPs, ML attack accuracies fall to about 50 %, equivalent to random guessing, while incurring very low hardware overhead.

Abstract

Strong physical unclonable function (PUF) is a promising solution for device authentication in resource-constrained applications but vulnerable to machine learning (ML) attacks. In order to resist attack, many defenses have been proposed in recent years. However, these defenses incur high hardware overhead, degenerate reliability and are inefficient against advanced ML attacks such as approximation attacks. To address these issues, we propose a Random Set-based Obfuscation (RSO) for Strong PUFs to resist ML attacks. The basic idea is that several stable responses are derived from the PUF itself and pre-stored as the set for obfuscation in the testing phase, and then a true random number generator is used to select any two keys to obfuscate challenges and responses with XOR operations. When the number of challenge-response pairs (CRPs) collected by the attacker exceeds the given threshold, the set will be updated immediately. In this way, ML attacks can be prevented with extremely low hardware overhead. Experimental results show that for a 64 × 64 Arbiter PUF, when the size of set is 32 and even if 1 million CRPs are collected by attackers, the prediction accuracies of the several ML attacks we use are about 50% which is equivalent to the random guessing.