COVER is a new video watermarking method that targets codec compression as its primary design goal. It embeds the watermark payload in the latent space of a frozen generative video autoencoder and recovers it by re‑encoding the received video into the same latent space. Using a differentiable codec surrogate bank, COVER achieves high bit accuracy across multiple codecs while keeping marked videos visually close to the originals.
By Yuxin Cao, Hao Yang, Ziqi Ding, Jie Hao, Wei Song
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
arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.
By Soohyeon Choi, Debin Gao, Yue Duan
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
The paper introduces mAVE, a training‑free watermarking framework for joint audio‑visual diffusion transformers that binds audio and video modalities through a session‑keyed cryptographic digest. mAVE separates public record retrieval from secret session authentication, enabling provider‑assisted verification without altering generator weights or training auxiliary networks. Experiments on LTX‑2 and MOVA demonstrate high true‑positive rates (99.8%) and negligible false positives, while maintaining comparable generation quality.
By Luyang Si, Leyi Pan, Dongsheng Ma, Lijie Wen
The paper introduces TaintedPixels, a proactive video‑protection technique that embeds subtle, structured perturbations into the blue channel of facial regions. These perturbations remain invisible in the original video but become noticeable after black‑box manipulation, thereby flagging deepfakes. Experiments on three off‑the‑shelf manipulation tools and two detectors show that TaintedPixels achieves the highest forgery detection rate while keeping visual distortion minimal (LPIPS = 0.0042), and a human study confirms that protected videos are rarely suspected, whereas forgeries from protected sources are identified as fake far more often than those from unprotected sources.
By Juan Hu, Shaojing Fan, Sanjay Saha, Marc Herrera, Terence Sim
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
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: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
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
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....