← Back to all news
arXiv Computer Vision By Xiaodong Wu, Qi Li, Xiangman Li, Zelin Zhang, Lingshuang Liu, Jianbing Ni

Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing

Read the original on arXiv Computer Vision →

The paper explores whether images with embedded watermarks can still be edited without damaging the watermark. It introduces SafeMark, a framework that adds a watermark‑decoding loss to the training objective of diffusion editors, ensuring that semantic edits preserve watermark integrity. Experiments across datasets and editing methods show that SafeMark maintains high watermark bit accuracy while producing quality edits, proving that watermark preservation and semantic editability can coexist.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 7

AngelFingerprint: A Traceable, Explainable, and White-Box Stealthy Watermark for Text-Guided Image Editing

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.

By Bo-Han Kung, Futa Waseda, Ching-Chun Chang, Isao Echizen, Shang-Tse Chen
ragdiffusionfine-tuningsafety
More like this →
arXiv Computer Vision
Sep 28

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

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.

By Haoyang Li, Ruoxi Sun, Qingqing Ye, Benjamin Zi Hao Zhao, Yaxin Xiao, Jason Xue, Haibo Hu
diffusionfine-tuningsafety
More like this →