相关论文: SLICE: Semantic Latent Injection via Compartmental…

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques.…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

The digital image manipulation and advancements in Generative AI, such as Deepfake, has raised significant concerns regarding the authenticity of images shared on social media. Traditional image forensic techniques, while helpful, are often…

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that…

Latent-based watermarks, integrated into the generation process of latent diffusion models (LDMs), simplify detection and attribution of generated images. However, recent black-box forgery attacks, where an attacker needs at least one…

As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed semantic signals - content-aware patterns that are designed to…

Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead,…

Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually…

The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep…

With the proliferation of AI-generated images, digital watermarking has become an essential safeguard for protecting intellectual property and mitigating malicious exploitation. Recent works on semantic watermarking have enabled efficient…

Real-world speech is often corrupted by multiple degradations simultaneously, including additive noise, reverberation, and nonlinear distortion. Diffusion-based enhancement methods perform well on single degradations but struggle with…

Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern…

As digital content becomes increasingly ubiquitous, the need for robust watermark removal techniques has grown due to the inadequacy of existing embedding techniques, which lack robustness. This paper introduces a novel Saliency-Aware…

Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of…

Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these…

Generative image modeling enables a wide range of applications but raises ethical concerns about responsible deployment. This paper introduces an active strategy combining image watermarking and Latent Diffusion Models. The goal is for all…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…

As AI-generated images become widespread, reliable watermarking is essential for content verification, copyright enforcement, and combating disinformation. Existing techniques rely on heuristic approaches and lack formal guarantees of…

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…