Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key
In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in a model by using learnable transformed images and allows us to remotely verify the ownership of the model. As a result, it is piracy-resistant, so the original watermark cannot be overwritten by a pirated watermark, and adding a new watermark decreases the model accuracy unlike most of the existing DNN watermarking methods. In addition, it does not require a special pre-defined training set or trigger set. We empirically evaluated the proposed method on the CIFAR-10 dataset. The results show that it was resilient against fine-tuning and pruning attacks while maintaining a high watermark-detection accuracy.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Multi-bit Natural Language Watermarking through Invariant Features
Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are…
Evolutionary Trigger Set Generation for DNN Black-Box Watermarking
The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownershi…
Piracy Resistant Watermarks for Deep Neural Networks
As companies continue to invest heavily in larger, more accurate and more robust deep learning models, they are exploring approaches to monetize their models while protecting their intellectual property. Model licensing …
Transfer LearningCSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics.…
Image GenerationROMark: A Robust Watermarking System Using Adversarial Training
The availability and easy access to digital communication increase the risk of copyrighted material piracy. In order to detect illegal use or distribution of data, digital watermarking has been proposed as a suitable too…
BIG-bench Machine Learning