Photonic Physical Unclonable Function Based on Integrated Neuromorphic Devices

In this work, we present a physical unclonable function, implemented using an integrated photonic neuromorphic device. The physical security feature in this case relies on the complex and unpredictable relation between hardware implemented complex weights at the hidden layer of a photonic reservoir computing scheme and the digital trainable weights at the output layer. Numerical simulations confirm that the neural weights are significantly affected by inevitable fabrication related imperfections of the silicon photonic platform. These features can be utilized as a physical root of trust, suitable for authentication/cryptographic applications. The proposed neuromorphic physical unclonable function concept, can be based on different types of neural networks, thus it paves the way for a wide range of photonic devices, able to simultaneously perform efficient non von Neumann computation and security related operations.