A Photonic Physically Unclonable Function's Resilience to Multiple-Valued Machine Learning Attacks
This work addresses security for integrated circuit identification, showing incremental improvements in assessing attack resilience for photonic PUFs.
The paper investigated the susceptibility of a photonic physically unclonable function (PUF) to multiple-valued-logic-based machine learning attacks, finding that approximately 1,000 challenge-response pairs are needed to train models that predict responses better than random chance, demonstrating resilience due to the difficulty of acquiring such data.
Physically unclonable functions (PUFs) identify integrated circuits using nonlinearly-related challenge-response pairs (CRPs). Ideally, the relationship between challenges and corresponding responses is unpredictable, even if a subset of CRPs is known. Previous work developed a photonic PUF offering improved security compared to non-optical counterparts. Here, we investigate this PUF's susceptibility to Multiple-Valued-Logic-based machine learning attacks. We find that approximately 1,000 CRPs are necessary to train models that predict response bits better than random chance. Given the significant challenge of acquiring a vast number of CRPs from a photonic PUF, our results demonstrate photonic PUF resilience against such attacks.