Robust-Wide: Robust Watermarking against Instruction-driven Image Editing

• URL: http://arxiv.org/abs/2402.12688v3
• Date: Wed, 17 Jul 2024 00:26:45 GMT
• Title: Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
• Authors: Runyi Hu, Jie Zhang, Ting Xu, Jiwei Li, Tianwei Zhang,
• Abstract summary: Malicious users can easily exploit instruction-driven image editing to create fake images. We propose Robust-Wide, the first robust watermarking methodology against instruction-driven image editing. Experiments demonstrate that Robust-Wide can effectively extract the watermark from the edited image with a low bit error rate of nearly 2.6%.
• Score: 21.69779516621288
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of trust and harm the rights of the original image owners. Watermarking is a common solution to trace such malicious behavior. Unfortunately, instruction-driven image editing can significantly change the watermarked image at the semantic level, making current state-of-the-art watermarking methods ineffective. To remedy it, we propose Robust-Wide, the first robust watermarking methodology against instruction-driven image editing. Specifically, we follow the classic structure of deep robust watermarking, consisting of the encoder, noise layer, and decoder. To achieve robustness against semantic distortions, we introduce a novel Partial Instruction-driven Denoising Sampling Guidance (PIDSG) module, which consists of a large variety of instruction injections and substantial modifications of images at different semantic levels. With PIDSG, the encoder tends to embed the watermark into more robust and semantic-aware areas, which remains in existence even after severe image editing. Experiments demonstrate that Robust-Wide can effectively extract the watermark from the edited image with a low bit error rate of nearly 2.6% for 64-bit watermark messages. Meanwhile, it only induces a neglectable influence on the visual quality and editability of the original images. Moreover, Robust-Wide holds general robustness against different sampling configurations and other popular image editing methods such as ControlNet-InstructPix2Pix, MagicBrush, Inpainting, and DDIM Inversion. Codes and models are available at https://github.com/hurunyi/Robust-Wide.

Related papers

• Lost in Edits? A $λ$-Compass for AIGC Provenance [119.95562081325552]
  We propose a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones. LambdaTracer is effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix or performed manually with editing software such as Adobe Photoshop.
  arXiv  Detail & Related papers  (2025-02-05T06:24:25Z)
• Invisible Watermarks: Attacks and Robustness [0.3495246564946556]
  We introduce novel improvements to watermarking robustness and minimize degradation on image quality during attack. We propose a custom watermark remover network which preserves one of the watermarking modalities while completely removing the other during decoding. Our evaluation suggests that 1) implementing the watermark remover model to preserve one of the watermark modalities when decoding the other modality slightly improves on the baseline performance, and that 2) LBA degrades the image significantly less compared to uniform blurring of the entire image.
  arXiv  Detail & Related papers  (2024-12-17T03:50:13Z)
• SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution [27.345134138673945]
  We propose SuperMark, a robust, training-free watermarking framework. SuperMark embeds the watermark into initial Gaussian noise using existing techniques. It then applies pre-trained Super-Resolution models to denoise the watermarked noise, producing the final watermarked image. For extraction, the process is reversed: the watermarked image is inverted back to the initial watermarked noise via DDIM Inversion, from which the embedded watermark is extracted. Experiments demonstrate that SuperMark achieves fidelity comparable to existing methods while significantly improving robustness.
  arXiv  Detail & Related papers  (2024-12-13T11:20:59Z)
• Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances [13.746887960091112]
  Large-scale text-to-image models can distort embedded watermarks during editing, posing challenges to copyright protection. We introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods. We propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques.
  arXiv  Detail & Related papers  (2024-10-24T14:28:32Z)
• Perceptive self-supervised learning network for noisy image watermark removal [59.440951785128995]
  We propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) Our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal.
  arXiv  Detail & Related papers  (2024-03-04T16:59:43Z)
• FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models [64.89896692649589]
  We propose FT-Shield, a watermarking solution tailored for the fine-tuning of text-to-image diffusion models. FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies.
  arXiv  Detail & Related papers  (2023-10-03T19:50:08Z)
• T2IW: Joint Text to Image & Watermark Generation [74.20148555503127]
  We introduce a novel task for the joint generation of text to image and watermark (T2IW) This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels. We demonstrate remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.
  arXiv  Detail & Related papers  (2023-09-07T16:12:06Z)
• Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust [55.91987293510401]
  Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. We introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs. Our watermark is semantically hidden in the image space and is far more robust than watermarking alternatives that are currently deployed.
  arXiv  Detail & Related papers  (2023-05-31T17:00:31Z)
• Supervised GAN Watermarking for Intellectual Property Protection [33.827150843939094]
  We propose a watermarking method for Generative Adversarial Networks (GANs) The aim is to watermark the GAN model so that any image generated by the GAN contains an invisible watermark (signature) Results show that our method can effectively embed an invisible watermark inside the generated images.
  arXiv  Detail & Related papers  (2022-09-07T20:52:05Z)
• A Robust Document Image Watermarking Scheme using Deep Neural Network [10.938878993948517]
  This paper proposes an end-to-end document image watermarking scheme using the deep neural network. Specifically, an encoder and a decoder are designed to embed and extract the watermark. A text-sensitive loss function is designed to limit the embedding modification on characters.
  arXiv  Detail & Related papers  (2022-02-26T05:28:52Z)
• WDNet: Watermark-Decomposition Network for Visible Watermark Removal [61.14614115654322]
  The uncertainty of the size, shape, color and transparency of watermarks set a huge barrier for image-to-image translation techniques. We combine traditional watermarked image decomposition into a two-stage generator, called Watermark-Decomposition Network (WDNet) The decomposition formulation enables WDNet to separate watermarks from the images rather than simply removing them.
  arXiv  Detail & Related papers  (2020-12-14T15:07:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.