Premium Access to Convolutional Neural Networks

TL;DR

This paper proposes a method to restrict access to neural networks by using a degraded implementation that can be corrected with a PIN, enhancing security for sensitive applications.

Contribution

It introduces a novel approach to control neural network access through parameter selection and a PIN-based correction mechanism.

Findings

Effective degradation of neural network accuracy in restricted mode

Successful correction of degraded performance using a PIN

Practical implementation demonstrated on a deep neural network

Abstract

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.