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.

We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 - 28. Join AI and data leaders for insightful talks and exciting networking opportunities. As organizations continue to migrate their workloads and shift to hybrid or remote work, cloud computing is growing at a rapid rate. Last week at the AWS Summit, according to Swami Sivasubramanian, the vice president of data, analytics and machine learning (ML) services at AWS, analysts project that between 5-15% of IT spend has moved to the cloud -- suggesting that organizations will continue to migrate even more of their workloads to the cloud in the future. The enterprise ecosystem is experiencing a disruption that's largely a result of more cloud-native applications coming to the scene. More companies are embracing a mix of both corporate devices and bring-your-own-device strategies.