Premium Access to Convolutional Neural Networks
This addresses security and access control for neural networks in applications like mobile devices, but it is incremental as it builds on existing neural network architectures.
The paper tackles the problem of restricting neural network access to privileged users by proposing a method that degrades performance for unauthorized users and restores it with a PIN, achieving a measurable accuracy gap between premium and degraded modes in experiments on a deep neural network.
Neural Networks (NNs) are today used for all our daily tasks; for instance, in mobile phones. We here want to show how to restrict their access to privileged users. Our solution relies on a degraded implementation which can be corrected thanks to a PIN. We explain how to select a few parameters in an NN so as to maximize the gap in the accuracy between the premium and the degraded modes. We report experiments on an implementation of our proposal on a deep NN to prove its practicability.