Machine Learning Resistant Amorphous Silicon Physically Unclonable Functions (PUFs)

We investigate usage of nonlinear wave chaotic amorphous silicon (a-Si) cavities as physically unclonable functions (PUF). Machine learning attacks on integrated electronic PUFs have been demonstrated to be very effective at modeling PUF behavior. Such attacks on integrated a-Si photonic PUFs are investigated through application of algorithms including linear regression, k-nearest neighbor, decision tree ensembles (random forests and gradient boosted trees), and deep neural networks (DNNs). We found that DNNs performed the best among all the algorithms studied but still …

algorithms application attacks behavior cs.lg electronic functions linear linear regression machine machine learning modeling physics.app-ph physics.optics regression silicon through usage