The paper introduces Latent Frequency Masking, an attack that removes or weakens invisible watermarks in AI-generated images by altering selected Fourier coefficients in the latent space. It demonstrates that this method can effectively compromise six diffusion watermarking techniques while maintaining image quality and running faster than existing attacks. The study provides a theoretical distortion bound and evaluates the attack on images from DiffusionDB and MS-COCO prompts.
By Kirill Aistov, Khaled Abud, Irina Serzhenko, Egor Kovalev, Aleksey Yakushev, Aleksandr Akimenkov, Dmitry Obydenkov, Yury Markin, Sergey Lavrushkin, Dmitriy Vatolin, Anastasia Antsiferova
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
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
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
The paper introduces the concept of watermark laundering, where an attacker uses a single reconstruction prompt on public foundation image models to produce a visually faithful output that renders invisible watermarks undecodable. The authors evaluate this failure mode across six OpenAI and Google image editing models, three watermarking schemes, and 1,800 reconstructions, finding that OpenAI models cause the strongest payload disruption while Nano Banana 2 shows vulnerability of DwtDct under high-fidelity reconstruction. Prompt ablation experiments reveal that the disruption is driven by the reconstruction pathway itself rather than any specific removal instruction, highlighting prompt-conditioned reconstruction as a distinct attack interface.
By Jidong Yang, Qi Li, Wei Zong, Yang-Wai Chow, Willy Susilo, Huaike Yu, Chunpeng Wang, Suo Gao
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...
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:2610.03166v1 Announce Type: cross
Abstract: Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks. Some attacks...
By Saibo Ye, Huajie Chen, Xin Guo, Le Yang, Chi Liu, Xiangyu Hu, Jingjing Guo, Tianqing Zhu
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.
By Chen-Hsiu Huang, Mario K\"oppen, Ja-Ling Wu
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
The proliferation of AI-generated images produced by Latent Diffusion Models (LDMs) has raised critical concerns regarding copyright infringement and misinformation. Although existing frequency-domain watermarking methods embed handcrafted geometric patterns into the initial latent noise prior to generation, they suffer from limited capacity and rigid pattern designs.
arXiv:2609.23586v1 Announce Type: new
Abstract: The rapid development of video generative models (VGMs) has enabled the generation of highly realistic synthetic videos, raising concerns about the int...
By Wenhong Huang, Jianwei Fei, Benedetta Tondi, Bin Ma, Fangjun Huang