Diffusion Model Watermarking

Ask about this topic

Overview

Diffusion model watermarking studies how to mark generated images, videos, audio, text, and model behavior so their origins or ownership can later be verified. Common approaches embed keyed signals in initial noise, latent or frequency representations, denoising steps, output pixels, or model weights, then use detectors, inversion, or learned decoders to recover them. Methods increasingly address temporal consistency in video, arbitrary token order in diffusion language models, and semantic binding that can expose forgery or tampering. The central challenge is balancing visual or textual quality and reliable detection against editing, regeneration, removal, and forgery attacks, whose effects depend strongly on the watermark and evaluation protocol.

Latest papers

CardsList

48 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

  1. CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation

    Oct 29, 2026Huangchao Song, Lingyun Yu, Cong Li +3Diffusion Model WatermarkingAI-Generated Image Watermarking

    University of Science and Technology of China · Tianjin University

  2. SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing

    Oct 22, 2026Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe +4Dataset WatermarkingDiffusion Model Watermarking

    University of Maryland · All Purpose AI

  3. WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models

    Oct 9, 2026Jie Cao, Qi Li, Chaklam Cheong +4Diffusion Model WatermarkingRobust Watermarking

    Department of Electrical and Computer Engineering, Queen’s University, Kingston, Canada · School of Computing, Queen’s University, Kingston, Canada · School of Computer Science, Nanjing University, Jiangsu, China

  4. Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies

    Oct 7, 2026Sung Ju Lee, Nam Ik ChoDiffusion Model WatermarkingAI-Generated Image Watermarking

    Department of ECE & INMC, Seoul National University, Korea

  5. Latent Watermarks under Generative Editing: A Benchmark and Analysis of Detection Survival

    Oct 7, 2026Sung Ju Lee, Nam Ik ChoAI-Generated Image WatermarkingDiffusion Model Watermarking

    Department of ECE & INMC Seoul National University Seoul, South Korea

  6. MARCO: The Radioactive Watermark for Protein Generative Models

    Oct 6, 2026Huajie Chen, Xin Guo, Yuchen Shi +7Robust WatermarkingDiffusion Model Watermarking

    Faculty of Data Science, City University of Macau. · CSIRO and Responsible AI Research (RAIR) Centre, Adelaide University.

  7. On the Intrinsic Limited Robustness of Latent-Based Watermarking

    Oct 6, 2026Cheng-Han Yeh, Kuan-chun Yu, Cheng-Chang Tsai +1Diffusion Model WatermarkingImage Corruption Robustness

    Institute of Information Science Academia Sinica Taipei, Taiwan (ROC)

  8. Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking

    Oct 1, 2026Kirill Aistov, Khaled Abud, Irina Serzhenko +8Diffusion Model WatermarkingWatermark Removal

    MSU AI Institute, Moscow, Russia · Trusted AI Research Center RAS, Moscow, Russia

  9. Persistent Watermarking of Text-to-Image Models

    Sep 30, 2026Dixi Yao, Kaiwen Chen, Tahseen Rabbani +1Diffusion Model WatermarkingRobust Watermarking

    University of Chicago

  10. TANGO: Watermarking Masked Diffusion Language Models in Token Pairs

    Sep 28, 2026Kasra Arabi, Nir Weinberger, Micah Goldblum +1Diffusion Model WatermarkingMasked Diffusion Models

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

    Sep 25, 2026Haoyang Li, Ruoxi Sun, Qingqing Ye +4AI-Generated Image WatermarkingDiffusion Model Watermarking

    The Hong Kong Polytechnic University · CSIRO’s Data61 · Macquarie University

  12. RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction

    Sep 14, 2026Zilai LiDiffusion Model InversionDiffusion Model Watermarking

    Independent Researcher

  13. DenMark: Robust Semantic Watermarking for Diffusion Language Models

    Sep 13, 2026Tianhao Ma, Weihao Xuan, Dong-Dong Wu +5Diffusion Model WatermarkingRobust Watermarking

    The University of Tokyo · RIKEN Center for Advanced Intelligence Project

  14. DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

    Sep 8, 2026Rui Bao, Zheng Gao, Xiaoyu Li +3Diffusion Model WatermarkingWatermark Removal

    University of New South Wales · Griffith University

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

    Sep 4, 2026Bo-Han Kung, Futa Waseda, Ching-Chun Chang +2AI-Generated Image WatermarkingDiffusion Model Watermarking

    National Taiwan University, Taiwan · National Institute of Informatics, Japan

  16. AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS

    Aug 23, 2026Timothy Tin-Long, Jian Zhu, Aidan Pine +1Audio WatermarkingRobust Watermarking

    National Research Council Canada, Canada · University of British Columbia, Canada

  17. SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields

    Aug 21, 2026Baixin Li, Haiyun HeDiffusion Model WatermarkingLLM Watermarking

    The Hong Kong University of Science and Technology (Guangzhou)

  18. DeepFreqMark: End-To-End Learnable Frequency-Domain Watermarking with Spherical Attack Simulation for Latent Diffusion Models

    Aug 10, 2026Chen-Hsiu Huang, Mario Köppen, Ja-Ling WuDiffusion Model WatermarkingLatent Diffusion Models

    National Taiwan University, Taipei, Taiwan · Kyushu Institute of Technology, Fukuoka, Japan

  19. IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

    Aug 4, 2026Xiaoyan Feng, Zheng Gao, Tong Guan +4Diffusion Model WatermarkingDiffusion-Based Image Generation

    1Griffith University · University of New South Wales · 3Zhejiang University

  20. Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

    Aug 1, 2026Jinyuan Liu, Tianshuo Cong, Pei Li +4Variational AutoencodersDiffusion Model Watermarking

    1Tsinghua University · 2Shandong University · 4Shandong Key Laboratory of Artificial Intelligence Security, Shandong University +5

  21. FARI: Robust One-Step Inversion for Watermarking in Diffusion Models

    Jul 29, 2026Jindong Yang, Han Fang, Weiming Zhang +2Diffusion ModelsDiffusion Model Watermarking

    University of Science and Technology of China · 2Anhui Province Key Laboratory of Digital Security

  22. Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models

    Jul 24, 2026Yebin Zheng, Haonan An, Guang Hua +2Diffusion Model WatermarkingLatent Diffusion Models

    Department of Infocomm Technology Singapore Institute of Technology · Department of Computer Science City University of Hong Kong · School of Electrical and Electronic Engineering Nanyang Technological University

  23. BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

    Jul 2, 2026Aryan PanditDiffusion Model WatermarkingLatent Diffusion Models

    PDPM Indian Institute of Information Technology, Jabalpur, India

  24. FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs

    Jun 22, 2026Wenlong Cheng, Yuan Gan, Yunqiu Xu +1Diffusion Model WatermarkingLatent Diffusion Models

    Northwest Normal University · The University of Tokyo · National University of Singapore +1

  25. Global Sketch-Based Watermarking for Diffusion Language Models

    Jun 3, 2026Daniel ZhaoDiffusion Model WatermarkingLLM Watermarking

    Harvard University

  26. Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing

    May 28, 2026Leyi Qi, Yiming Li, Siyuan Liang +2Diffusion Model WatermarkingRandomized Smoothing

    Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Computer Science and Engineering, Texas A&M University, USA

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

    May 19, 2026Xiaodong Wu, Qi Li, Xiangman Li +3Diffusion Model WatermarkingText-Guided Image Editing

    Queen’s University · University of Waterloo

  28. PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection

    May 10, 2026Minh Quoc Duong, Chun Tong Lei, Chun Pong LauDiffusion Model InversionDiffusion Model Watermarking

    City University of Hong Kong

  29. Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles

    May 7, 2026Enoal Gesny, Eva GiboulotDiffusion Model WatermarkingRobust Watermarking

    Inria, Rennes, France

  30. Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks

    May 6, 2026Mohd Ruhul Ameen, Akif Islam, Nadim Mahmud +1Diffusion Model WatermarkingWatermark Removal

    College of Engineering and Computer Science, Marshall University, Huntington, WV, USA · Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh · Miami University, Oxford, OH 45056, USA