Digital Passport: A Novel Technological Strategy for Intellectual Property Protection of Convolutional Neural Networks

TL;DR

This paper introduces a digital passport system for neural networks that prevents unauthorized use by embedding a digital signature, effectively protecting intellectual property while maintaining network performance for authorized users.

Contribution

It presents a novel digital passport embedding method into neural networks that deters unauthorized usage and preserves functionality for verified users.

Findings

Unauthorized usage reduces network accuracy by 33% to 82%.

The digital passport system effectively detects fake passports.

Networks with valid passports maintain high accuracy.

Abstract

In order to prevent deep neural networks from being infringed by unauthorized parties, we propose a generic solution which embeds a designated digital passport into a network, and subsequently, either paralyzes the network functionalities for unauthorized usages or maintain its functionalities in the presence of a verified passport. Such a desired network behavior is successfully demonstrated in a number of implementation schemes, which provide reliable, preventive and timely protections against tens of thousands of fake-passport deceptions. Extensive experiments also show that the deep neural network performance under unauthorized usages deteriorate significantly (e.g. with 33% to 82% reductions of CIFAR10 classification accuracies), while networks endorsed with valid passports remain intact.