Robust watermarking using generative priors against image editing: From benchmarking to advances

S Lu, Z Zhou, J Lu, Y Zhu, AWK Kong - arXiv preprint arXiv:2410.18775, 2024 - arxiv.org
Current image watermarking methods are vulnerable to advanced image editing techniques
enabled by large-scale text-to-image models. These models can distort embedded …

Self-improving diffusion models with synthetic data

S Alemohammad, AI Humayun, S Agarwal… - arXiv preprint arXiv …, 2024 - arxiv.org
The artificial intelligence (AI) world is running out of real data for training increasingly large
generative models, resulting in accelerating pressure to train on synthetic data …

To Authenticity, and Beyond! Building safe and fair generative AI upon the three pillars of provenance

J Collomosse, A Parsons - IEEE Computer Graphics and …, 2024 - ieeexplore.ieee.org
Provenance facts, such as who made an image and how, can provide valuable context for
users to make trust decisions about visual content. Against a backdrop of inexorable …

Swift: Semantic watermarking for image forgery thwarting

G Evennou, V Chappelier, E Kijak, T Furon - arXiv preprint arXiv …, 2024 - arxiv.org
This paper proposes a novel approach towards image authentication and tampering
detection by using watermarking as a communication channel for semantic information. We …

Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation

Y Wang, X Zhu, G Ye, S Zhang, X Wei - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
DNN-based watermarking methods are rapidly developing and delivering impressive
performances. Recent advances achieve resolution-agnostic image watermarking by …

Watermark Anything with Localized Messages

T Sander, P Fernandez, A Durmus, T Furon… - arXiv preprint arXiv …, 2024 - arxiv.org
Image watermarking methods are not tailored to handle small watermarked areas. This
restricts applications in real-world scenarios where parts of the image may come from …

InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance

R Xu, D Lei, Y Li, D Lowe, A Gorevski, M Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
The proliferation of AI-generated images has intensified the need for robust content
authentication methods. We present InvisMark, a novel watermarking technique designed …

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking

X Zhang, Z Tang, Z Xu, R Li, Y Xu, B Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
With the rapid growth of generative AI and its widespread application in image editing, new
risks have emerged regarding the authenticity and integrity of digital content. Existing …

DeepSync: Affine Transform Recovery Via Convolutional Neural Networks for Watermark Synchronization

DG Chachlakis, M Yousuf, T Filler - Electronic Imaging, 2024 - library.imaging.org
In the context of digital watermarking of images/video, template based techniques rely on the
insertion of a signal template to aid recovery of the watermark after transforms (rotation …

Disentangled Style Domain for Implicit -Watermark Towards Copyright Protection

J Huang, Z Guo, G Luo, Z Qian, S Li, X Zhang - The Thirty-eighth Annual … - openreview.net
Text-to-image models have shown surprising performance in high-quality image generation,
while also raising intensified concerns about the unauthorized usage of personal dataset in …