The paper introduces RAIN, a lightweight, prompt‑free extractor for semantic watermarks in diffusion models. By decomposing the endpoint recovery into an image‑like anchor and a noise‑oriented residual, RAIN avoids iterative inversion and reduces the computational cost compared to existing one‑step methods. The approach leverages extended flow matching and conditional regression to recover a useful noise statistic near the high‑SNR image endpoint, enabling efficient one‑step extraction.
arXiv:2607. 26723v1 Announce Type: cross Abstract: Inversion-based watermarking is a promising approach to authenticate diffusion-generated images, yet practical use is bottlenecked by inversion that is both slow and error-prone.
arXiv:2608. 10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored.
DRIFT is a black‑box attack that removes diffusion watermarks by combining partial forward diffusion with stochastic reverse resampling. It limits the source information available to a fixed‑depth recovery pipeline and uses stochastic reversal to explore alternative noise‑driven paths, refining fidelity only on updates rejected by the same verifier. Across nine watermarks, DRIFT achieves 98–100% attack success and the best image quality without requiring secret keys, verifier internals, or per‑image gradient optimization.
DRIFT is a black‑box attack that removes diffusion watermarks by deflecting the generative trajectory. It combines partial forward diffusion with stochastic reverse resampling to limit the source information available to a fixed‑depth recovery pipeline and to explore alternative noise‑driven paths. Across nine watermarks, DRIFT achieves 98–100% success while preserving image quality, without requiring secret keys, verifier internals, or per‑image gradient optimization.
FeatMark is a watermarking framework that protects images from text‑to‑image diffusion model mimicry attacks by embedding small, scene‑consistent micro‑features instead of pixel‑level perturbations. It constructs domain‑specific feature banks, selects executable features, and injects them via mask‑guided concept editing to create highly localized, natural edits. Experiments on VGGFace2, CelebA‑HQ, and WikiArt show FeatMark remains robust against ten strong watermark removal attacks and several adaptive attacks, with minimal impact on perceptual quality and extending to video mimicry scenarios.
Pixel‑Space Diffusion via Observation Operators introduces a new framework for pixel‑space diffusion models that addresses a scale‑time mismatch in existing methods. By replacing fixed full‑image supervision with a time‑indexed observation trajectory that progresses from coarse structures to the full image, the model aligns supervision with the natural recovery order of image details. The approach employs Gaussian‑Lanczos operators and a GL‑CoDA decoder to refine features progressively, resulting in faster convergence and higher generation quality, achieving an FID of 1.52 on ImageNet‑256.
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual....
arXiv:2605.16879v2 Announce Type: replace Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for...
arXiv:2603.23463v2 Announce Type: replace-cross Abstract: Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text...
arXiv:2608. 08999v1 Announce Type: cross Abstract: The proliferation of AI-generated images produced by Latent Diffusion Models (LDMs) has raised critical concerns regarding copyright infringement and misinformation.
arXiv:2609.39623v1 Announce Type: new Abstract: The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images wh...
AngelFingerprint introduces a watermarking framework for text-guided image editing that embeds the editing prompt’s CLIP text embedding directly into the diffusion model’s weights via a LoRA module. The watermark is recoverable from image pixels alone, providing an explainable trace of the edit while remaining stealthy even under full white-box access. Experiments on the MagicBrush dataset show the extractor achieves 86% top‑1 accuracy in 200‑way prompt retrieval, outperforming prompt inversion methods.