ROMark: A Robust Watermarking System Using Adversarial Training

Wen, Bingyang; Aydöre, Sergül

doi:10.48550/arxiv.1910.01221

Cited by 13 publications

(31 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ReDMark [6] adds a circular convolutional layer that diffuses the watermark signal all over the image. Finally, ROMark [5] uses robust optimization with worst-case attack as if an adversary were trying to remove the mark. For more details, we refer to the review [21].…”

Section: Related Workmentioning

confidence: 99%

“…Examples include directly marking into the semantic space resulting from a supervised training over a given set of classes like ImageNet [3], or explicitly training a watermarking network to be invariant to a set of image perturbations. In this case, networks are usually encoder-decoder architectures trained end-to-end for watermarking [4,5,6,7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Watermarking Images in Self-Supervised Latent Spaces

Fernandez¹,

Sablayrolles²,

Furon³

et al. 2021

Preprint

View full text Add to dashboard Cite

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. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained endto-end for watermarking. Our implementation and models will be made publicly available.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Watermarking Images in Self-Supervised Latent Spaces

Fernandez¹,

Sablayrolles²,

Furon³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning based methods for image watermarking [1,18,38,42,45] achieved great progress in recent years. HiDDeN [45] was one of the first deep image watermarking methods that achieved good performance compared to traditional watermarking approaches.…”

Section: Watermarkingmentioning

confidence: 99%

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings

Yoo¹,

Chang²,

Luo³

et al. 2021

Preprint

View full text Add to dashboard Cite

Digital watermarking is widely used for copyright protection. Traditional 3D watermarking approaches or commercial software are typically designed to embed messages into 3D meshes, and later retrieve the messages directly from distorted/undistorted watermarked 3D meshes. Retrieving messages from 2D renderings of such meshes, however, is still challenging and underexplored. We introduce a novel end-to-end learning framework to solve this problem through: 1) an encoder to covertly embed messages in both mesh geometry and textures; 2) a differentiable renderer to render watermarked 3D objects from different camera angles and under varied lighting conditions; 3) a decoder to recover the messages from 2D rendered images. From extensive experiments, we show that our models learn to embed information visually imperceptible to humans, and to reconstruct the embedded information from 2D renderings robust to 3D distortions. In addition, we demonstrate that our method can be generalized to work with different renderers, such as ray tracers and real-time renderers.

show abstract

“…However, these attacks are not adversarial since they do not adapt with the watermarking model during training. Recently, ROMark [38] applied a simple form of adversarial training where the distortion type and distortion strength are adaptively selected to minimize the decoding accuracy.…”

Section: Watermarkingmentioning

confidence: 99%

Distortion Agnostic Deep Watermarking

Luo

Zhan

Chang

et al. 2020

Preprint

View full text Add to dashboard Cite

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learningbased methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually unknown and non-differentiable. In this paper, we propose a new framework for distortionagnostic watermarking, where the image distortion is not explicitly modeled during training. Instead, the robustness of our system comes from two sources: adversarial training and channel coding. Compared to training on a fixed set of distortions and noise levels, our method achieves comparable or better results on distortions available during training, and better performance on unknown distortions.

show abstract

ROMark: A Robust Watermarking System Using Adversarial Training

Cited by 13 publications

References 5 publications

Watermarking Images in Self-Supervised Latent Spaces

Watermarking Images in Self-Supervised Latent Spaces

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings

Distortion Agnostic Deep Watermarking

Contact Info

Product

Resources

About