# Performance Comparison of Contemporary DNN Watermarking Techniques

arXiv: https://arxiv.org/abs/1811.03713 · HTML: https://mlsanity.com/paper/1811.03713/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2018.

## Built on by (most cited first, 5 of 5)

- [Deep Intellectual Property Protection: A Survey](https://mlsanity.com/paper/2304.14613/) (2023)
- [Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks](https://mlsanity.com/paper/2304.11285/) (2023)
- [EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection](https://mlsanity.com/paper/2312.12049/) (2023)
- [Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects](https://mlsanity.com/paper/2108.09065/) (2021)
- [Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms](https://mlsanity.com/paper/2608.02656/) (2026)

## Abstract (arXiv)

DNNs shall be considered as the intellectual property (IP) of the model builder due to the impeding cost of designing/training a highly accurate model. Research attempts have been made to protect the authorship of the trained model and prevent IP infringement using DNN watermarking techniques. In this paper, we provide a comprehensive performance comparison of the state-of-the-art DNN watermarking methodologies according to the essential requisites for an effective watermarking technique. We identify the pros and cons of each scheme and provide insights into the underlying rationale. Empirical results corroborate that DeepSigns framework proposed in [4] has the best overall performance in terms of the evaluation metrics. Our comparison facilitates the development of pending watermarking approaches and enables the model owner to deploy the watermarking scheme that satisfying her requirements.