mlsanityData to 14 Oct 2026

MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models

arXiv 2509.10569 ↗First posted 11 Sep 2025cs.CR cs.AI cs.MMcited by 5

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framework for streamlined watermarking algorithm integrations and user-friendly interfaces; a mechanism visualization suite that intuitively showcases added and extracted watermark patterns to aid public understanding; and a comprehensive evaluation module offering standard implementations of 24 tools across three essential aspects - detectability, robustness, and output quality - plus 8 automated evaluation pipelines. Through MarkDiffusion, we seek to assist researchers, enhance public awareness and engagement in generative watermarking, and promote consensus while advancing research and applications.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 27 of its 34 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

27 of 34 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking24 Jan
  2. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization6 Nov
  3. 2024An Undetectable Watermark for Generative Image Models9 Oct
  4. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models7 Apr
  5. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  6. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  5. 2023A Watermark for Large Language Modelscited by 725
  6. 2023ModelScope Text-to-Video Technical Reportcited by 658
  7. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  8. 2023Undetectable Watermarks for Language Modelscited by 226
  9. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  10. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 134
  11. 2023A Semantic Invariant Robust Watermark for Large Language Modelscited by 112
  12. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 112
9 more
  1. 2024MarkLLM: An Open-Source Toolkit for LLM Watermarkingcited by 95
  2. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 91
  3. 2023An Unforgeable Publicly Verifiable Watermark for Large Language Modelscited by 65
  4. 2023Typology of Risks of Generative Text-to-Image Modelscited by 55
  5. 2023On Exact Inversion of DPM-Solverscited by 47
  6. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 21
  7. 2025Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?cited by 19
  8. 2024Can Watermarked LLMs be Identified by Users via Crafted Prompts?cited by 13
  9. 2024WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documentscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Watermarking Should Be Treated as a Monitoring Primitivecited by 2
  2. 2026MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulationcited by 1
  3. 2026mAVE: A Watermark for Joint Audio-Visual Generation Modelscited by 0
  4. 2026Representation Learning in Diffusion and Flow-based Model: An Application Aspectcited by 0
  5. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining
  2. 2025SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
  3. 2023A Recipe for Watermarking Diffusion Models
  4. 2025Image Watermarking of Generative Diffusion Models
  5. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Models
  6. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
  7. 2025TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
  8. 2024Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending