mlsanityData to 7 Oct 2026

StegaStamp: Invisible Hyperlinks in Physical Photographs

arXiv 1904.05343 ↗First posted 10 Apr 2019cs.CVcited by 256

Not on the map. Why?

Cited by 89 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think about this is physical photographs that have unique QR codes invisibly embedded within them. This paper presents an architecture, algorithms, and a prototype implementation addressing this vision. Our key technical contribution is StegaStamp, a learned steganographic algorithm to enable robust encoding and decoding of arbitrary hyperlink bitstrings into photos in a manner that approaches perceptual invisibility. StegaStamp comprises a deep neural network that learns an encoding/decoding algorithm robust to image perturbations approximating the space of distortions resulting from real printing and photography. We demonstrates real-time decoding of hyperlinks in photos from in-the-wild videos that contain variation in lighting, shadows, perspective, occlusion and viewing distance. Our prototype system robustly retrieves 56 bit hyperlinks after error correction - sufficient to embed a unique code within every photo on the internet.

Key facts. Cited by 256 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 17; 2023: 36; 2024: 58; 2025: 62; 2026: 68.

256 papers.

Sort:

By area:

  1. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  2. 2021MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressioncited by 108
  3. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  4. 2024Generalizable and Animatable Gaussian Head Avatarcited by 95
  5. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  6. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  7. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  8. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attackscited by 75
  9. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  10. 2024An Undetectable Watermark for Generative Image Modelscited by 74
  11. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 62
  12. 2022Data Feedback Loops: Model-driven Amplification of Dataset Biasescited by 59
38 more
  1. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 54
  2. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  3. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
  4. 2024Watermark Anything with Localized Messagescited by 49
  5. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 48
  6. 2021Deep Model Intellectual Property Protection via Deep Watermarkingcited by 47
  7. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  8. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  9. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  10. 2023DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Modelscited by 41
  11. 2021Tracing Text Provenance via Context-Aware Lexical Substitutioncited by 40
  12. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
  13. 2022Proactive Image Manipulation Detectioncited by 35
  14. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  15. 2024A Watermark-Conditioned Diffusion Model for IP Protectioncited by 34
  16. 2023CopyRNeRF: Protecting the CopyRight of Neural Radiance Fieldscited by 33
  17. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 33
  18. 2022StegaNeRF: Embedding Invisible Information within Neural Radiance Fieldscited by 32
  19. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  20. 2022Imperceptible Backdoor Attack: From Input Space to Feature Representationcited by 27
  21. 2024A Transfer Attack to Image Watermarkscited by 26
  22. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Modelscited by 26
  23. 2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 25
  24. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  25. 2021Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderingscited by 23
  26. 2021Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganographycited by 23
  27. 2022PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenescited by 22
  28. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  29. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  30. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Modelcited by 21
  31. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  32. 2023Large-capacity and Flexible Video Steganography via Invertible Neural Networkcited by 20
  33. 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splattingcited by 20
  34. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  35. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19
  36. 2022FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakescited by 18
  37. 2024Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Modelcited by 18
  38. 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18

50 most cited of 256 All 256 (JSON)