mlsanityData to 14 Oct 2026

Watermark Anything with Localized Messages

arXiv 2411.07231 ↗First posted 11 Nov 2024cs.CV cs.CRcited by 53

Not on the map. Why?

Cited by 20 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolution and without perceptual constraints, then post-trained for imperceptibility and multiple watermarks. Experiments show that WAM is competitive with state-of-the art methods in terms of imperceptibility and robustness, especially against inpainting and splicing, even on high-resolution images. Moreover, it offers new capabilities: WAM can locate watermarked areas in spliced images and extract distinct 32-bit messages with less than 1 bit error from multiple small regions -- no larger than 10% of the image surface -- even for small 256x256 images. Training and inference code and model weights are available at https://github.com/facebookresearch/watermark-anything.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 59 of its 119 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

59 of 119 references.

References · 59

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2023Segment Anythingcited by 8,234
  8. 2020End-to-End Object Detection with Transformerscited by 7,414
  9. 2017Mask R-CNNcited by 7,277
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  12. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
38 more
  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  3. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  4. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  5. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  6. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  7. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  8. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  9. 2023Segment Anything in High Qualitycited by 376
  10. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 352
  11. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
  12. 2023Fast Segment Anythingcited by 290
  13. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  14. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  15. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 187
  16. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  17. 2023A Recipe for Watermarking Diffusion Modelscited by 141
  18. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 111
  19. 2021MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressioncited by 110
  20. 2021Watermarking Images in Self-Supervised Latent Spacescited by 94
  21. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 91
  22. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 91
  23. 2020Distortion Agnostic Deep Watermarkingcited by 90
  24. 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 78
  25. 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
  26. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  27. 2018ReDMark: Framework for Residual Diffusion Watermarking on Deep Networkscited by 57
  28. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 57
  29. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 53
  30. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 51
  31. 2023On Exact Inversion of DPM-Solverscited by 47
  32. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRAcited by 46
  33. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  34. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 40
  35. 2022Proactive Image Manipulation Detectioncited by 35
  36. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 31
  37. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 28
  38. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Modelcited by 21

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 25; 2026: 25.

53 papers.

Sort:

By area:

  1. 2024Video Seal: Open and Efficient Video Watermarkingcited by 48
  2. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  3. 2025SynthID-Image: Image watermarking at internet scalecited by 31
  4. 2025Watermarking Autoregressive Image Generationcited by 16
  5. 2025SEAL: Semantic Aware Image Watermarkingcited by 15
  6. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 15
  7. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 12
  8. 2024LVMark: Robust Watermark for Latent Video Diffusion Modelscited by 9
  9. 2025Mask Image Watermarkingcited by 9
  10. 2025Watermarking Without Standards Is Not AI Governancecited by 9
  11. 2025Geometric Image Synchronization with Deep Watermarkingcited by 7
  12. 2025LACONIC: A 3D Layout Adapter for Controllable Image Creationcited by 6
38 more
  1. 2025NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Modelscited by 6
  2. 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Modelscited by 5
  3. 2025IConMark: Robust Interpretable Concept-Based Watermark For AI Imagescited by 3
  4. 2025Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectorscited by 3
  5. 2025DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detectioncited by 3
  6. 2026Learning to Watermark in the Latent Space of Generative Modelscited by 3
  7. 2025CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splattingcited by 2
  8. 2025VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrievalcited by 2
  9. 2025EditTrack: Detecting and Attributing AI-assisted Image Editingcited by 2
  10. 2025Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesiscited by 1
  11. 2025Your Text Encoder Can Be An Object-Level Watermarking Controllercited by 1
  12. 2025MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarkscited by 1
  13. 2025LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generationcited by 1
  14. 2025Low-Compute Watermark Removal via Dual-Domain Natural Projectioncited by 1
  15. 2026Unifying Watermarking via Dimension-Aware Mappingcited by 1
  16. 2026WaterVIB: Learning Minimal Sufficient Watermark Representations via Variational Information Bottleneckcited by 1
  17. 2026SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Modelscited by 1
  18. 2026Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspectivecited by 1
  19. 2026Learning Probabilistic Embeddings for Unsupervised Action Segmentationcited by 1
  20. 2025Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shufflingcited by 0
  21. 2025Where is the Watermark? Interpretable Watermark Detection at the Block Levelcited by 0
  22. 2025WaTeRFlow: Watermark Temporal Robustness via Flow Consistencycited by 0
  23. 2026Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Modelscited by 0
  24. 2026TokenTrace: Multi-Concept Attribution through Watermarked Token Recoverycited by 0
  25. 2026TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarkingcited by 0
  26. 2026Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridgescited by 0
  27. 2026SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defensecited by 0
  28. 2026ADD for Multi-Bit Image Watermarkingcited by 0
  29. 2026Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategycited by 0
  30. 2026RAW: Robust Avatar Watermarking -- Benchmarking and Baselinecited by 0
  31. 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarkingcited by 0
  32. 2026APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Imagescited by 0
  33. 2026TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectoriescited by 0
  34. 2026NAWE: Digital Watermarking with Neural-Assisted Watermark Extractioncited by 0
  35. 2026Disentangle and Drop: Robust Universal Removal of Image Watermarks via Reconstructive Grayscale Residual Decompositioncited by 0
  36. 2026Where Does the Watermark Hide? Push-Pull Disentanglement for Invisible Watermark Removalcited by 0
  37. 2026Residual Transferability in Neural Image Watermarkingcited by 0
  38. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Invisible Watermarks: Attacks and Robustness
  2. 2023WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning
  3. 2024WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
  4. 2026What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking
  5. 2024WAPITI: A Watermark for Finetuned Open-Source LLMs
  6. 2024Black-Box Detection of Language Model Watermarks
  7. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
  8. 2025TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity