Edge Deep Learning Model Protection via Neuron Authorization. (arXiv:2303.12397v1 [cs.CR])

With the development of deep learning processors and accelerators, deep
learning models have been widely deployed on edge devices as part of the
Internet of Things. Edge device models are generally considered as valuable
intellectual properties that are worth for careful protection. Unfortunately,
these models have a great risk of being stolen or illegally copied. The
existing model protections using encryption algorithms are suffered from high
computation overhead which is not practical due to the limited computing
capacity on edge …

algorithms authorization computation deep learning development device devices edge edge devices encryption great high internet internet of things neuron processors protection risk stolen things