DNN Intellectual Property Protection: Taxonomy, Methods, Attack Resistance, and Evaluations

The training and creation of deep learning model is usually costly, thus it can be regarded as an intellectual property (IP) of the model creator. However, malicious users who obtain high-performance models may illegally copy, redistribute, abuse the models, or use the models to provide prediction services without permission. To deal with such security threats, a few deep neural networks (DNN) IP protection methods have been proposed in recent years. This paper attempts to provide a review of the existing DNN IP protection works and also an outlook. First, we propose the first taxonomy for DNN IP protection methods in terms of five attributes: scenario, capacity, type, mechanism, and attack resistance. Second, we present a survey on existing DNN IP protection works in terms of the above five attributes, especially focusing on the challenges these methods face, whether these methods can provide proactive protection, and their resistances to different levels of attacks. Third, we analyze the potential attacks on DNN IP protection methods. Fourth, we propose a systematic evaluation method for DNN IP protection methods. Lastly, challenges and future works are presented.