WaveMark introduces a wavelet‑domain watermarking technique that embeds messages into the initial noise of diffusion models, distributing keyed replicas across spatial positions, wavelet orientations, and scales to enhance robustness. The method encodes each carrier with a randomized bit via magnitude projection of four latent channel coefficients, yielding a clear decoding margin. Experiments on SD2.1 with SDP and MS‑COCO Captions show perfect bit accuracy without attacks and over 88% accuracy against state‑of‑the‑art removal attacks, outperforming existing baselines while preserving image quality.
By Jie Cao, Qi Li, Chaklam Cheong, Yutong Jin, Enze Yu, Zelin Zhang, Jianbing Ni
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
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.
By Jie Cao, Qi Li, Zelin Zhang, Xiaodong Wu, Lingshuang Liu, Xiangman Li, Jianbing Ni
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:2609.39024v1 Announce Type: new
Abstract: Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyrigh...
By Dixi Yao, Kaiwen Chen, Tahseen Rabbani, Tian Li
The paper introduces VeriFi, a watermarking framework that protects face images from AI‑generated manipulation. It embeds a compact semantic latent watermark to preserve content, localizes pixel‑level edits without explicit payloads, and simulates realistic deepfake attacks to improve robustness. Experiments on CelebA‑HQ and FFHQ show that VeriFi outperforms existing methods in robustness, localization accuracy, and recovery quality.
By Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong Chang
arXiv:2609.40031v1 Announce Type: cross
Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated co...
By Khaled Abud, Aleksey Yakushev, Aleksandr Akimenkov, Irina Serzhenko, Kirill Aistov, Egor Kovalev, Dmitry Obydenkov, Sergey Lavrushkin, Anastasia Antsiferova, Dmitriy Vatolin, Yury Markin, Kirill Lukianov
Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated content and ensuring traceable sources to prevent man...
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
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...
By Yoonseo Kim, Seungwoo Baek, Junyoung Park
The paper presents a two‑axis taxonomy for watermarking diffusion‑generated images, categorizing methods by insertion mechanism and signal‑bearing representation. It formalizes a $z_T$‑Fourier verification pipeline and applies the taxonomy to three protocol‑bounded case studies that explore frequency integrity, persistence under editing, and VAE‑latent phase modulation. The authors also delineate four content‑level attack families, propose evaluation protocols, and suggest temporal extensions for video, offering a framework for protocol‑aware comparisons rather than a universal ranking.
By Sung Ju Lee, Nam Ik Cho
IRIS is a training‑free watermarking scheme for diffusion‑generated images that binds a watermark to the image’s visual semantics. It derives an intrinsic ring identifier from a content code of the non‑watermarked image and injects it late in the generation trajectory, ensuring the mark survives common processing while breaking under semantic changes or foreign images. Experiments on three prompt datasets show IRIS reliably detects watermarks, maintains fidelity to the original image, and resists forgery techniques that defeat other marks.
By Xiaoyan Feng, Zheng Gao, Tong Guan, Rui Bao, Bokang Zeng, Xiaoyu Li, Jiaojiao Jiang