Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Models

TL;DR

This paper surveys active intellectual property protection methods for deep learning models, focusing on active authorization and user management, highlighting the limited research in this emerging area and discussing future challenges.

Contribution

It systematically reviews the concept, attributes, evaluation metrics, existing work, potential attacks, and future directions of active DNN copyright protection.

Findings

Active copyright protection involves authorization control and user management.

Limited research exists on active DNN copyright protection.

The paper discusses challenges and future research directions.

Abstract

The intellectual property protection of deep learning (DL) models has attracted increasing serious concerns. Many works on intellectual property protection for Deep Neural Networks (DNN) models have been proposed. The vast majority of existing work uses DNN watermarking to verify the ownership of the model after piracy occurs, which is referred to as passive verification. On the contrary, we focus on a new type of intellectual property protection method named active copyright protection, which refers to active authorization control and user identity management of the DNN model. As of now, there is relatively limited research in the field of active DNN copyright protection. In this review, we attempt to clearly elaborate on the connotation, attributes, and requirements of active DNN copyright protection, provide evaluation methods and metrics for active copyright protection, review and analyze existing work on active DL model intellectual property protection, discuss potential attacks that active DL model copyright protection techniques may face, and provide challenges and future directions for active DL model intellectual property protection. This review is helpful to systematically introduce the new field of active DNN copyright protection and provide reference and foundation for subsequent work.