mlsanityData to 7 Oct 2026

Watermarking Images in Self-Supervised Latent Spaces

arXiv 2112.09581 ↗First posted 17 Dec 2021cs.CV cs.LGcited by 90

Not on the map. Why?

Cited by 40 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained end-to-end for watermarking. The code is available at github.com/facebookresearch/ssl_watermarking

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 17 Dec 2021.

Builds on

18 of 42 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2013Intriguing properties of neural networkscited by 5,114
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  12. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
6 more
  1. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  2. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  3. 2020Distortion Agnostic Deep Watermarkingcited by 88
  4. 2018ReDMark: Framework for Residual Diffusion Watermarking on Deep Networkscited by 55
  5. 2021Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganographycited by 23
  6. 2019ROMark: A Robust Watermarking System Using Adversarial Trainingcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 33; 2025: 27; 2026: 18.

90 papers.

Sort:

By area:

  1. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  2. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  3. 2022On the duality between contrastive and non-contrastive self-supervised learningcited by 107
  4. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  5. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  6. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  7. 2024An Undetectable Watermark for Generative Image Modelscited by 74
  8. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 54
  9. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
  10. 2024Watermark Anything with Localized Messagescited by 49
  11. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  12. 2024SoK: Watermarking for AI-Generated Contentcited by 43
38 more
  1. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  2. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 33
  3. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  4. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  5. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  6. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  7. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Modelcited by 21
  8. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  9. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19
  10. 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18
  11. 2025Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integritycited by 14
  12. 2025SEAL: Semantic Aware Image Watermarkingcited by 13
  13. 2025Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Imagecited by 12
  14. 2024Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?cited by 10
  15. 2025On the Difficulty of Constructing a Robust and Publicly-Detectable Watermarkcited by 9
  16. 2022Active Image Indexingcited by 8
  17. 2023Intrinsic Self-Supervision for Data Quality Auditscited by 8
  18. 2023Steal My Artworks for Fine-tuning? A Watermarking Framework for Detecting Art Theft Mimicry in Text-to-Image Modelscited by 8
  19. 2024Watermark-based Attribution of AI-Generated Contentcited by 8
  20. 2024SWIFT: Semantic Watermarking for Image Forgery Thwartingcited by 8
  21. 2024Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoningcited by 8
  22. 2023Warfare:Breaking the Watermark Protection of AI-Generated Contentcited by 7
  23. 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guaranteescited by 7
  24. 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Spacecited by 7
  25. 2024Continuous fake media detection: adapting deepfake detectors to new generative techniquescited by 6
  26. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 6
  27. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retrainingcited by 5
  28. 2025Guidance Watermarking for Diffusion Modelscited by 5
  29. 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Modelscited by 4
  30. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Surveycited by 4
  31. 2024Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generationcited by 3
  32. 2024Evaluating Durability: Benchmark Insights into Multimodal Watermarkingcited by 3
  33. 2025On the Coexistence and Ensembling of Watermarkscited by 3
  34. 2025ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clusteringcited by 3
  35. 2025Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectorscited by 3
  36. 2023A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarkingcited by 2
  37. 2024SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attackscited by 2
  38. 2024ScreenMark: Watermarking Arbitrary Visual Content on Screencited by 2

50 most cited of 90 All 90 (JSON)