Scholarlink

<p>This paper introduces a novel Generative Adversarial Model for Image Watermarking called <i>WatermarkGAN</i>, which is designed to embed imperceptible digital watermarks into GAN-generated images, ensuring copyright protection with limited training data. The approach effectively safeguards against unauthorized use while preserving both image quality and robustness under distortions. The method achieves a high watermark embedding capacity of 100 bits per image and maintains 90% to 94% extraction accuracy, even in the presence of common image processing attacks such as compression, Gaussian noise, and rotation. It integrates a CNN-based watermark embedding and retrieval system with StyleGAN2-ADA for high-fidelity image generation. Through extensive experimentation on two datasets, CelebA (25K images, 128<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>128 resolution) and ZEN (9K images, 256<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>256 resolution), the approach demonstrates its effectiveness, with FID scores of 5.54 and 11.35, respectively. The paper also examines the impact of hyperparameter tuning and retraining to optimize watermark robustness and image quality. The results confirm that <i>WatermarkGAN</i> consistently generates high-quality images while providing secure and distortion-resistant watermarking. This framework offers a practical and scalable solution for digital content protection, ensuring that designers’ identities are preserved in published images. Our method achieved 100% accuracy in DeepFake detection when applied to watermarked images, demonstrating its high effectiveness in classifying authentic and modified images.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deepfake detection via image watermarking: A generative adversarial model approach with limited data

  • 期刊论文

  • 发表日期：

    2025年8月27日

查看全文
  • Ali H. Shareef,
  • Hajer Ghodhbani,
  • Tarek M. Hamdani,
  • Mounir Ben Ayed,
  • Khmaies Ouahada,
  • Habib Chabchoub,
  • Adel M. Alimi

摘要

This paper introduces a novel Generative Adversarial Model for Image Watermarking called WatermarkGAN, which is designed to embed imperceptible digital watermarks into GAN-generated images, ensuring copyright protection with limited training data. The approach effectively safeguards against unauthorized use while preserving both image quality and robustness under distortions. The method achieves a high watermark embedding capacity of 100 bits per image and maintains 90% to 94% extraction accuracy, even in the presence of common image processing attacks such as compression, Gaussian noise, and rotation. It integrates a CNN-based watermark embedding and retrieval system with StyleGAN2-ADA for high-fidelity image generation. Through extensive experimentation on two datasets, CelebA (25K images, 128 \(\times\) 128 resolution) and ZEN (9K images, 256 \(\times\) 256 resolution), the approach demonstrates its effectiveness, with FID scores of 5.54 and 11.35, respectively. The paper also examines the impact of hyperparameter tuning and retraining to optimize watermark robustness and image quality. The results confirm that WatermarkGAN consistently generates high-quality images while providing secure and distortion-resistant watermarking. This framework offers a practical and scalable solution for digital content protection, ensuring that designers’ identities are preserved in published images. Our method achieved 100% accuracy in DeepFake detection when applied to watermarked images, demonstrating its high effectiveness in classifying authentic and modified images.