mlsanityData to 7 Oct 2026

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

arXiv 2410.18775 ↗First posted 24 Oct 2024cs.CV cs.AI cs.CRcited by 105

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods against a wide range of image editing techniques, including image regeneration, global editing, local editing, and image-to-video generation. Through extensive evaluations of eleven representative watermarking methods against prevalent editing techniques, we demonstrate that most methods fail to detect watermarks after such edits. To address this limitation, we propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques while maintaining high image quality. Our approach involves two key innovations: (1) we analyze the frequency characteristics of image editing and identify that blurring distortions exhibit similar frequency properties, which allows us to use them as surrogate attacks during training to bolster watermark robustness; (2) we leverage a large-scale pretrained diffusion model SDXL-Turbo, adapting it for the watermarking task to achieve more imperceptible and robust watermark embedding. Experimental results show that our method achieves outstanding watermarking performance under various image editing techniques, outperforming existing methods in both image quality and robustness. Code is available at https://github.com/Shilin-LU/VINE.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 90 of its 110 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

90 of 110 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024LaWa: Using Latent Space for In-Generation Image Watermarking11 Aug
  2. 2024JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits6 Jun
  3. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining8 Apr
  4. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models7 Apr
  5. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space30 Mar
  6. 2023Invisible Image Watermarks Are Provably Removable Using Generative AI2 Jun
  7. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  8. 2023Watermarking Diffusion Model21 May
  9. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection10 May
  10. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar
  11. 2023A Recipe for Watermarking Diffusion Models17 Mar

Other references · 79

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  12. 2022Flow Matching for Generative Modelingcited by 5,426
38 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  9. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  10. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  11. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  12. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  13. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  14. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  15. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  16. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  17. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  18. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  19. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  20. 2023Adversarial Diffusion Distillationcited by 741
  21. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  22. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  23. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  24. 2023Erasing Concepts from Diffusion Modelscited by 530
  25. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  26. 2022Diffusion Models for Adversarial Purificationcited by 469
  27. 2022Blended Latent Diffusioncited by 430
  28. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 411
  29. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  30. 2022CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformerscited by 305
  31. 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 298
  32. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
  33. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 266
  34. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  35. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 256
  36. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 229
  37. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  38. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 193

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 58; 2026: 43.

105 papers.

Sort:

By area:

  1. 2025Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Conceptscited by 61
  2. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 50
  3. 2025CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Processcited by 50
  4. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 48
  5. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  6. 2025GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modelingcited by 43
  7. 2025OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrievalcited by 40
  8. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 39
  9. 2025ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLMcited by 36
  10. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  11. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
  12. 2025HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrievalcited by 32
38 more
  1. 2025Towards Universal Modal Tracking with Online Dense Temporal Token Learningcited by 30
  2. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  3. 2025DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editingcited by 29
  4. 2025DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Modelscited by 28
  5. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  6. 2026HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrievalcited by 24
  7. 2025From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspectivecited by 22
  8. 2024KinMo: Kinematic-aware Human Motion Understanding and Generationcited by 21
  9. 2025UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Datasetcited by 16
  10. 2025All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splattingcited by 15
  11. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 14
  12. 2026HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrievalcited by 14
  13. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 13
  14. 2026TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrievalcited by 13
  15. 2025CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentationcited by 12
  16. 2025Show and Polish: Reference-Guided Identity Preservation in Face Video Restorationcited by 12
  17. 2025Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognitioncited by 11
  18. 2025Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Modelscited by 11
  19. 2025Mask Image Watermarkingcited by 9
  20. 2025BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignmentcited by 9
  21. 2025Intentional Gesture: Deliver Your Intentions with Gestures for Speechcited by 8
  22. 2025UITron-Speech: Towards Automated GUI Agents Based on Speech Instructionscited by 7
  23. 2025Noise Matters: Optimizing Matching Noise for Diffusion Classifierscited by 7
  24. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  25. 2025Nested Unfolding Network for Real-World Concealed Object Segmentationcited by 7
  26. 2025STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adaptercited by 6
  27. 2026From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmarkcited by 6
  28. 2025Overview of the NLPCC 2025 Shared Task 4: Multi-modal, Multilingual, and Multi-hop Medical Instructional Video Question Answering Challengecited by 5
  29. 2025BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editingcited by 5
  30. 2026RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Detailscited by 5
  31. 2025Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detectioncited by 4
  32. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
  33. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  34. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Surveycited by 4
  35. 2025Diffusion-Based Image Editing for Breaking Robust Watermarkscited by 4
  36. 2026MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generationcited by 4
  37. 2025ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clusteringcited by 3
  38. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3

50 most cited of 105 All 105 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023A Somewhat Robust Image Watermark against Diffusion-based Editing Models
  2. 2024An Undetectable Watermark for Generative Image Models
  3. 2025On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing
  4. 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Models
  5. 2024Robustness of Watermarking on Text-to-Image Diffusion Models
  6. 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
  7. 2026ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
  8. 2025Spread them Apart: Towards Robust Watermarking of Generated Content