mlsanityData to 14 Oct 2026

Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey

arXiv 2510.02384 ↗First posted 30 Sep 2025cs.CR cs.CVcited by 5

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

Abstract (arXiv)

The rapid progress of Generative Artificial Intelligence (GenAI) has enabled the effortless synthesis of high-quality visual content, while simultaneously raising pressing concerns about intellectual property protection, authenticity, and accountability. Among various countermeasures, watermarking has emerged as a fundamental mechanism for tracing provenance, distinguishing AI-generated images from natural content, and supporting trustworthy digital ecosystems. This paper presents a comprehensive survey of AI-generated image watermarking, systematically reviewing the field from five perspectives: (1) the formalization and fundamental components of image watermarking systems; (2) existing watermarking methodologies and their comparative characteristics; (3) evaluation metrics in terms of visual fidelity, embedding capacity, and detectability; (4) known vulnerabilities under malicious attacks and recent advances in secure and robust watermarking designs; and (5) open challenges, emerging trends, and future research directions. The survey seeks to offer researchers a holistic understanding of watermarking technologies for AI-generated images and to facilitate their continued advancement toward secure and responsible AI-generated content practices.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 59 of its 100 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

59 of 100 references.

Closest ancestors · 23

Same direction, newest first

  1. 2025Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID27 Aug
  2. 2025When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting4 Jul
  3. 2025Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models6 Jun
  4. 2025Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image27 Apr
  5. 2025Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models21 Apr
  6. 2025WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion15 Apr
  7. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models6 Dec
  8. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models4 Dec
  9. 2024AI-generated Image Detection: Passive or Watermark?20 Nov
  10. 2024SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI18 Nov
  11. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization6 Nov
  12. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances24 Oct
11 more
  1. 2024An Undetectable Watermark for Generative Image Models9 Oct
  2. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA18 May
  3. 2024Stable Signature is Unstable: Removing Image Watermark from Diffusion Models12 May
  4. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models7 Apr
  5. 2024A Watermark-Conditioned Diffusion Model for IP Protection16 Mar
  6. 2024Pseudorandom Error-Correcting Codes14 Feb
  7. 2024Attack-Resilient Image Watermarking Using Stable Diffusion8 Jan
  8. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks29 Sep
  9. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  10. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators14 Apr
  11. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar

Other references · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2020Denoising Diffusion Implicit Modelscited by 9,781
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  12. 2021Zero-Shot Text-to-Image Generationcited by 4,288
24 more
  1. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  2. 2024A Survey on Large Language Models for Code Generationcited by 658
  3. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  4. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  5. 2021Multi-attentional Deepfake Detectioncited by 341
  6. 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Modelscited by 324
  7. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  8. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  9. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  10. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 97
  11. 2021Watermarking Images in Self-Supervised Latent Spacescited by 94
  12. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 91
  13. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 91
  14. 2020Distortion Agnostic Deep Watermarkingcited by 90
  15. 2024Controllable Text Generation for Large Language Models: A Surveycited by 57
  16. 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
  17. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 50
  18. 2023On Exact Inversion of DPM-Solverscited by 47
  19. 2025On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspectivecited by 41
  20. 2024A Transfer Attack to Image Watermarkscited by 27
  21. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 24
  22. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 21
  23. 2025Zero-Shot Styled Text Image Generation, but Make It Autoregressivecited by 13
  24. 2013Digital Watermarking for Image AuthenticationBased on Combined DCT, DWT and SVD Transformationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulationcited by 1
  2. 2025DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learningcited by 0
  3. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0
  4. 2026Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptationcited by 0
  5. 2026WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SoK: Watermarking for AI-Generated Content
  2. 2025Watermarking for AI Content Detection: A Review on Text, Visual, and Audio Modalities
  3. 2025IConMark: Robust Interpretable Concept-Based Watermark For AI Images
  4. 2023Evading Watermark based Detection of AI-Generated Content
  5. 2024Watermark-based Attribution of AI-Generated Content
  6. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
  7. 2025Watermarking across Modalities for Content Tracing and Generative AI
  8. 2025On-Device Watermarking: A Socio-Technical Imperative For Authenticity In The Age of Generative AI