mlsanityData to 7 Oct 2026

WAVES: Benchmarking the Robustness of Image Watermarks

arXiv 2401.08573 ↗First posted 16 Jan 2024cs.CV cs.CR cs.LGcited by 89

Not on the map. Why?

Cited by 45 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming the limitations of current evaluation methods. WAVES integrates detection and identification tasks and establishes a standardized evaluation protocol comprised of a diverse range of stress tests. The attacks in WAVES range from traditional image distortions to advanced, novel variations of diffusive, and adversarial attacks. Our evaluation examines two pivotal dimensions: the degree of image quality degradation and the efficacy of watermark detection after attacks. Our novel, comprehensive evaluation reveals previously undetected vulnerabilities of several modern watermarking algorithms. We envision WAVES as a toolkit for the future development of robust watermarks. The project is available at https://wavesbench.github.io/

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 16 Jan 2024.

Builds on

38 of 57 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  11. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  12. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
26 more
  1. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  2. 2018Variational image compression with a scale hyperpriorcited by 910
  3. 2022Diffusion Models for Adversarial Purificationcited by 469
  4. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  5. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 376
  6. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  7. 2018Adversarial Attacks and Defences: A Surveycited by 259
  8. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  9. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  10. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  11. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 179
  12. 2023How Robust is Google's Bard to Adversarial Image Attacks?cited by 177
  13. 2019Robust Invisible Video Watermarking with Attentioncited by 144
  14. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  15. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  16. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  17. 2021MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressioncited by 108
  18. 2021Watermarking Images in Self-Supervised Latent Spacescited by 90
  19. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attackscited by 75
  20. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  21. 2017Generating Steganographic Images via Adversarial Trainingcited by 57
  22. 2018ReDMark: Framework for Residual Diffusion Watermarking on Deep Networkscited by 55
  23. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  24. 2020A Loss Function for Generative Neural Networks Based on Watson's Perceptual Modelcited by 39
  25. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  26. 2023Securing Deep Generative Models with Universal Adversarial Signaturecited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 24; 2025: 30; 2026: 35.

89 papers.

Sort:

By area:

  1. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  2. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  3. 2024An Undetectable Watermark for Generative Image Modelscited by 74
  4. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 48
  5. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  6. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  7. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  8. 2024A Transfer Attack to Image Watermarkscited by 26
  9. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  10. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 19
  11. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 18
  12. 2024Stable Signature is Unstable: Removing Image Watermark from Diffusion Modelscited by 16
38 more
  1. 2025Watermarking Autoregressive Image Generationcited by 15
  2. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  3. 2025Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Modelscited by 12
  4. 2024Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?cited by 10
  5. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 10
  6. 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Spacecited by 7
  7. 2024AI-generated Image Detection: Passive or Watermark?cited by 7
  8. 2025First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challengecited by 7
  9. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 6
  10. 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Modelscited by 5
  11. 2024Securing the Future of GenAI: Policy and Technologycited by 4
  12. 2025Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarioscited by 4
  13. 2025Visual Watermarking in the Era of Diffusion Models: Advances and Challengescited by 4
  14. 2025VideoMarkBench: Benchmarking Robustness of Video Watermarkingcited by 4
  15. 2025A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarkscited by 4
  16. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Surveycited by 4
  17. 2024Evaluating Durability: Benchmark Insights into Multimodal Watermarkingcited by 3
  18. 2024Certifiably Robust Image Watermarkcited by 3
  19. 2024Watermarking Visual Concepts for Diffusion Modelscited by 3
  20. 2025RoHOI: Robustness Benchmark for Human-Object Interaction Detectioncited by 3
  21. 2025IConMark: Robust Interpretable Concept-Based Watermark For AI Imagescited by 3
  22. 2024Protecting Copyrighted Material with Unique Identifiers in Large Language Model Trainingcited by 2
  23. 2024DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarkingcited by 2
  24. 2024Invisible Watermarks: Attacks and Robustnesscited by 2
  25. 2024SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Trainingcited by 2
  26. 2025Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulationcited by 2
  27. 2025CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attentioncited by 2
  28. 2025When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Settingcited by 2
  29. 2025Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprintscited by 2
  30. 2026IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation Scenarioscited by 2
  31. 2026Towards Robust Content Watermarking Against Removal and Forgery Attackscited by 2
  32. 2026Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Imagescited by 2
  33. 2024Robustness of Watermarking on Text-to-Image Diffusion Modelscited by 1
  34. 2025Beyond Release: Access Considerations for Generative AI Systemscited by 1
  35. 2025Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Modelscited by 1
  36. 2025Your Text Encoder Can Be An Object-Level Watermarking Controllercited by 1
  37. 2025Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Modelscited by 1
  38. 2025KGMark: A Diffusion Watermark for Knowledge Graphscited by 1

50 most cited of 89 All 89 (JSON)