DEEPJUDGE: A Testing Framework for Copyright Protection of Deep Learning Models

Deep learning (DL) models have become one of the most valuable assets in modern society, and those most complex ones require millions of dollars for the model development. As a result, unauthorized duplication or reproduction of DL models can lead to copyright infringement and cause huge economic losses to model owners. In this work, we present Deepjudge, a testing framework for DL copyright protection. Deep Judgequantitatively tests the similarities between two DL models: a victim model and a suspect model. It leverages a diverse set of testing metrics and efficient test case generation algorithms to produce a chain of supporting evidence to help determine whether a suspect model is a copy of the victim model. Our experiments confirm the effectiveness of Deepjudge under typical model copyright infringement scenarios. The tool has been made publicly available at https://github.com/Testing4AI/DeepJudge. A demo video can be found at https://www.youtube.com/watch?v=LhNeo615YOE.