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

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.

arXiv commentThis paper proposes a new timely IPR solution that embed digital passports into CNN models to prevent the unauthorized network usage (i.e. infringement) by paralyzing the networks while maintaining its functionality for verified users

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Embedding Watermarks into Deep Neural Networks
• Adversarial Frontier Stitching for Remote Neural Network Watermarking
• A Robust Blind Watermarking Using Convolutional Neural Network
• DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models
• DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networks

Cited by in corpus (1)

• Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluations