Pith. sign in

CycleGANWM: A CycleGAN watermarking method for ownership verification

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Due to the proliferation and widespread use of deep neural networks (DNN), their Intellectual Property Rights (IPR) protection has become increasingly important. This paper presents a novel model watermarking method for an unsupervised image-to-image translation (I2IT) networks, named CycleGAN, which leverage the image translation visual quality and watermark embedding. In this method, a watermark decoder is trained initially. Then the decoder is frozen and used to extract the watermark bits when training the CycleGAN watermarking model. The CycleGAN watermarking (CycleGANWM) is trained with specific loss functions and optimized to get a good performance on both I2IT task and watermark embedding. For watermark verification, this work uses statistical significance test to identify the ownership of the model from the extract watermark bits. We evaluate the robustness of the model against image post-processing and improve it by fine-tuning the model with adding data augmentation on the output images before extracting the watermark bits. We also carry out surrogate model attack under black-box access of the model. The experimental results prove that the proposed method is effective and robust to some image post-processing, and it is able to resist surrogate model attack.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

Dynamic watermarks in images generated by diffusion models

cs.CV · 2025-02-13 · reject · novelty 4.0

The paper claims a two-branch watermarking method that embeds a fixed QR code in a diffusion model's latent process and a dynamic watermark in generated images, enabling source verification.

citing papers explorer

Showing 1 of 1 citing paper.

  • Dynamic watermarks in images generated by diffusion models cs.CV · 2025-02-13 · reject · none · ref 20 · internal anchor

    The paper claims a two-branch watermarking method that embeds a fixed QR code in a diffusion model's latent process and a dynamic watermark in generated images, enabling source verification.