Robust watermarking with double detector-discriminator approach

• URL: http://arxiv.org/abs/2006.03921v1
• Date: Sat, 6 Jun 2020 17:15:45 GMT
• Title: Robust watermarking with double detector-discriminator approach
• Authors: Marcin Plata, Piotr Syga
• Abstract summary: We present a novel deep framework for a watermarking - a technique of embedding a transparent message into an image in a way that allows retrieving the message from a copy. Our framework outperforms recent methods in the context of robustness against spectrum of attacks. We also present our double detector-discriminator approach - a scheme to detect and discriminate if the image contains the embedded message or not.
• Score: 0.5330240017302621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we present a novel deep framework for a watermarking - a technique of embedding a transparent message into an image in a way that allows retrieving the message from a (perturbed) copy, so that copyright infringement can be tracked. For this technique, it is essential to extract the information from the image even after imposing some digital processing operations on it. Our framework outperforms recent methods in the context of robustness against not only spectrum of attacks (e.g. rotation, resizing, Gaussian smoothing) but also against compression, especially JPEG. The bit accuracy of our method is at least 0.86 for all types of distortions. We also achieved 0.90 bit accuracy for JPEG while recent methods provided at most 0.83. Our method retains high transparency and capacity as well. Moreover, we present our double detector-discriminator approach - a scheme to detect and discriminate if the image contains the embedded message or not, which is crucial for real-life watermarking systems and up to now was not investigated using neural networks. With this, we design a testing formula to validate our extended approach and compared it with a common procedure. We also present an alternative method of balancing between image quality and robustness on attacks which is easily applicable to the framework.

Related papers

• SWIFT: Semantic Watermarking for Image Forgery Thwarting [12.515429388063534]
  We modify the HiDDeN deep-learning watermarking architecture to embed and extract high-dimensional real vectors representing image captions. Our method improves significantly on both malign and benign edits.
  arXiv  Detail & Related papers  (2024-07-26T09:50:13Z)
• JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits [76.25962336540226]
  JIGMARK is a first-of-its-kind watermarking technique that enhances robustness through contrastive learning. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits.
  arXiv  Detail & Related papers  (2024-06-06T03:31:41Z)
• Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation [12.224148236368997]
  We present Resolution-Agnostic Image WaterMarking (RAIMark) framework by watermarking implicit neural representation (INR) of image. Our method does not rely on the previous reduction process by directly watermarking the continuous signal instead of image pixels.
  arXiv  Detail & Related papers  (2024-05-14T06:26:58Z)
• Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations [6.948186032020995]
  The proposed method is based on the existing HiDDeN architecture that uses deep learning for watermark encoding and decoding. We add new noise layers to this architecture, namely for a differentiable JPEG estimation, rotation, rescaling, translation, shearing and mirroring. In conclusion, the proposed method can be used to protect images when viewed on consumers' devices.
  arXiv  Detail & Related papers  (2024-02-14T10:18:00Z)
• RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees [33.61946642460661]
  This paper introduces a robust and agile watermark detection framework, dubbed as RAW. We employ a classifier that is jointly trained with the watermark to detect the presence of the watermark. We show that the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image.
  arXiv  Detail & Related papers  (2024-01-23T22:00:49Z)
• Practical Deep Dispersed Watermarking with Synchronization and Fusion [10.633580224539337]
  We propose a practical deep textbfDispersed textbfWatermarking with textbfSynchronization and textbfFusion. Our blind watermarking can achieve better performance: averagely improve the bit accuracy by 5.28% and 5.93% against single and combined attacks, respectively.
  arXiv  Detail & Related papers  (2023-10-23T03:34:05Z)
• 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)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• Docmarking: Real-Time Screen-Cam Robust Document Image Watermarking [97.77394585669562]
  Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by applying on the screen a unique identifying watermark as semi-transparent image. Watermark image is static and stays on the screen all the time thus watermark present on every captured photograph of the screen.
  arXiv  Detail & Related papers  (2023-04-25T09:32:11Z)
• Watermarking Images in Self-Supervised Latent Spaces [75.99287942537138]
  We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time.
  arXiv  Detail & Related papers  (2021-12-17T15:52:46Z)
• Exploring Structure Consistency for Deep Model Watermarking [122.38456787761497]
  The intellectual property (IP) of Deep neural networks (DNNs) can be easily stolen'' by surrogate model attack. We propose a new watermarking methodology, namely structure consistency'', based on which a new deep structure-aligned model watermarking algorithm is designed.
  arXiv  Detail & Related papers  (2021-08-05T04:27:15Z)

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.