Watermark Faker: Towards Forgery of Digital Image Watermarking
This addresses a security risk for copyright protection systems, but is incremental as it applies existing deep learning methods to a new attack scenario.
The paper tackles the problem of generating fake watermarked images to circumvent digital watermarking protection, using a generative adversarial learning approach with U-Net, and shows it can effectively crack watermarkers in spatial and frequency domains.
Digital watermarking has been widely used to protect the copyright and integrity of multimedia data. Previous studies mainly focus on designing watermarking techniques that are robust to attacks of destroying the embedded watermarks. However, the emerging deep learning based image generation technology raises new open issues that whether it is possible to generate fake watermarked images for circumvention. In this paper, we make the first attempt to develop digital image watermark fakers by using generative adversarial learning. Suppose that a set of paired images of original and watermarked images generated by the targeted watermarker are available, we use them to train a watermark faker with U-Net as the backbone, whose input is an original image, and after a domain-specific preprocessing, it outputs a fake watermarked image. Our experiments show that the proposed watermark faker can effectively crack digital image watermarkers in both spatial and frequency domains, suggesting the risk of such forgery attacks.