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

arXiv: https://arxiv.org/abs/2310.09822 · HTML: https://mlsanity.com/paper/2310.09822/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 15 Oct 2023.

## Builds on (most cited first, 18 of 18)

- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [Embedding Watermarks into Deep Neural Networks](https://mlsanity.com/paper/1701.04082/) (2017)
- [Model Watermarking for Image Processing Networks](https://mlsanity.com/paper/2002.11088/) (2020)
- [Robust Watermarking of Neural Network with Exponential Weighting](https://mlsanity.com/paper/1901.06151/) (2019)
- [Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluations](https://mlsanity.com/paper/2011.13564/) (2020)
- [Watermarking Graph Neural Networks by Random Graphs](https://mlsanity.com/paper/2011.00512/) (2020)
- [Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication](https://mlsanity.com/paper/2104.04268/) (2021)
- [AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption](https://mlsanity.com/paper/2105.13697/) (2021)
- [Neural network fragile watermarking with no model performance degradation](https://mlsanity.com/paper/2208.07585/) (2022)
- [Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples](https://mlsanity.com/paper/2205.04145/) (2022)
- [Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection](https://mlsanity.com/paper/2011.08960/) (2020)
- [Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images](https://mlsanity.com/paper/2104.09203/) (2021)
- [A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access](https://mlsanity.com/paper/2109.00224/) (2021)
- [Device-Bind Key-Storageless Hardware AI Model IP Protection: A PUF and Permute-Diffusion Encryption-Enabled Approach](https://mlsanity.com/paper/2212.11133/) (2022)
- [Protect the Intellectual Property of Dataset against Unauthorized Use](https://mlsanity.com/paper/2109.07921/) (2021)
- [PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Models](https://mlsanity.com/paper/2206.02541/) (2022)
- [InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features](https://mlsanity.com/paper/2210.07481/) (2022)
- [Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition](https://mlsanity.com/paper/2110.09814/) (2021)

## Built on by (most cited first, 2 of 2)

- [Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions](https://mlsanity.com/paper/2406.10573/) (2024)
- [Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses](https://mlsanity.com/paper/2508.19641/) (2025)

## Abstract (arXiv)

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.