Related papers: The Stable Signature: Rooting Watermarks in Latent…

In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile…

Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and regeneration attacks. Recent semantic-aware watermarking…

In this paper, we introduce a simple yet effective tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data…

Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models are trained on billions of internet-sourced images, raising…

Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate…

The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collapse. To address this…

Recent advances in deep generative models have led to the development of methods capable of synthesizing high-quality, realistic images. These models pose threats to society due to their potential misuse. Prior research attempted to…

Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermarking systems, the robustness of these schemes against forgery…

Current large-scale generative models have impressive efficiency in generating high-quality images based on text prompts. However, they lack the ability to precisely control the size and position of objects in the generated image. In this…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introduced new challenges in intellectual property protection and…

Recent advancements in large language models (LLMs) have highlighted the risk of misusing them, raising the need for accurate detection of LLM-generated content. In response, a viable solution is to inject imperceptible identifiers into…

The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive…

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…

This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image…

Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection…

We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a…

The current work is focusing on the implementation of a robust watermarking algorithm for digital images, which is based on an innovative spread spectrum analysis algorithm for watermark embedding and on a content-based image retrieval…

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding…

Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strategies operate by altering the decoder of an existing language…