Intellectual property protection for deep learning model and dataset intelligence

With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significance of these remarkable models has soared. However, acquiring well-trained models is costly and resource-intensive. It requires a considerably high-quality dataset, substantial investment in dedicated architecture design, expensive computational resources, and efforts to develop technical expertise. Consequently, protecting the Intellectual Property (IP) of well-trained models is becoming a priority. Despite the importance of IP protection, most existing surveys focus narrowly on model level intelligence, with limited attention given to protecting the valuable dataset intelligence. This indicates a significant gap in existing surveys regarding comprehensive strategies for safeguarding the IP of datasets. In this survey, we address the gap by presenting a comprehensive overview of both model and dataset IP protection in DL context. Firstly, according to the requirements for effective IP protection design, this work systematically summarizes the general and scheme-specific performance evaluation metrics. Secondly, from proactive IP infringement prevention and reactive IP ownership verification perspectives, it comprehensively investigates and analyzes the existing IP protection methods for both dataset and model intelligence. Additionally, from the standpoint of training settings, it delves into the unique challenges that distributed learning poses to IP protection compared to centralized settings. Furthermore, this work examines various attacks faced by deep IP protection techniques. Finally, we outline prospects for promising future directions that may act as a guide for innovative research.