mlsanityData to 14 Oct 2026

Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms

arXiv 2212.12678 ↗First posted 24 Dec 2022cs.MM cs.CVcited by 61

Not on the map. Why?

Cited by 23 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Blind watermarking provides powerful evidence for copyright protection, image authentication, and tampering identification. However, it remains a challenge to design a watermarking model with high imperceptibility and robustness against strong noise attacks. To resolve this issue, we present a framework Combining the Invertible and Non-invertible (CIN) mechanisms. The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks. For the invertible part, we develop a diffusion and extraction module (DEM) and a fusion and split module (FSM) to embed and extract watermarks symmetrically in an invertible way. For the non-invertible part, we introduce a non-invertible attention-based module (NIAM) and the noise-specific selection module (NSM) to solve the asymmetric extraction under a strong noise attack. Extensive experiments demonstrate that our framework outperforms the current state-of-the-art methods of imperceptibility and robustness significantly. Our framework can achieve an average of 99.99% accuracy and 67.66 dB PSNR under noise-free conditions, while 96.64% and 39.28 dB combined strong noise attacks. The code will be available in https://github.com/rmpku/CIN.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 24 Dec 2022.

Builds on

33 of 52 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  5. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  6. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  7. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  8. 2018Invertible Residual Networkscited by 365
  9. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  10. 2019Residual Flows for Invertible Generative Modelingcited by 257
  11. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
  12. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
21 more
  1. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  2. 2018i-RevNet: Deep Invertible Networkscited by 137
  3. 2021MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressioncited by 110
  4. 2021Invertible Image Signal Processingcited by 94
  5. 2020Invertible Image Rescalingcited by 92
  6. 2020Distortion Agnostic Deep Watermarkingcited by 90
  7. 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
  8. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
  9. 2018ReDMark: Framework for Residual Diffusion Watermarking on Deep Networkscited by 57
  10. 2019C-Flow: Conditional Generative Flow Models for Images and 3D Point Cloudscited by 50
  11. 2019MintNet: Building Invertible Neural Networks with Masked Convolutionscited by 35
  12. 2021Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganographycited by 24
  13. 2019Reversible GANs for Memory-efficient Image-to-Image Translationcited by 19
  14. 2019ROMark: A Robust Watermarking System Using Adversarial Trainingcited by 18
  15. 2021IICNet: A Generic Framework for Reversible Image Conversioncited by 13
  16. 2017A Robust Blind Watermarking Using Convolutional Neural Networkcited by 11
  17. 2021A Brief Survey on Deep Learning Based Data Hidingcited by 9
  18. 2019Hybrid blind robust image watermarking technique based on DFT-DCT and Arnold transformcited by 8
  19. 2020Modeling Lost Information in Lossy Image Compressioncited by 8
  20. 2020Robust Data Hiding Using Inverse Gradient Attentioncited by 5
  21. 2019Hiding Data in Images Using Cryptography and Deep Neural Networkcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 10; 2025: 23; 2026: 23.

61 papers.

Sort:

By area:

  1. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 111
  2. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 110
  3. 2024Watermark Anything with Localized Messagescited by 53
  4. 2023WavMark: Watermarking for Audio Generationcited by 50
  5. 2024Video Seal: Open and Efficient Video Watermarkingcited by 48
  6. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 44
  7. 2023DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Modelscited by 43
  8. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 35
  9. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  10. 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarkingcited by 34
  11. 2024V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protectioncited by 28
  12. 2024LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarkscited by 21
38 more
  1. 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18
  2. 2023Robust Identity Perceptual Watermark Against Deepfake Face Swappingcited by 17
  3. 2025Watermarking Autoregressive Image Generationcited by 16
  4. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 15
  5. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 12
  6. 2025MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structurecited by 10
  7. 2025DiffMark: Diffusion-based Robust Watermark Against Deepfakescited by 7
  8. 2025Geometric Image Synchronization with Deep Watermarkingcited by 7
  9. 2025WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networkscited by 5
  10. 2025FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarkscited by 4
  11. 2025ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generationcited by 4
  12. 2024Investigating Deep Watermark Security: An Adversarial Transferability Perspectivecited by 3
  13. 2025Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectorscited by 3
  14. 2025VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inferencecited by 3
  15. 2026Learning to Watermark in the Latent Space of Generative Modelscited by 3
  16. 2025Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulationcited by 2
  17. 2026All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermarkcited by 2
  18. 2024Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representationcited by 1
  19. 2025WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusioncited by 1
  20. 2025MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarkscited by 1
  21. 2025LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generationcited by 1
  22. 2025Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary sizecited by 1
  23. 2025WavInWav: Time-domain Speech Hiding via Invertible Neural Networkcited by 1
  24. 2026DeMark: A Query-Free Black-Box Attack on Deepfake Watermarking Defensescited by 1
  25. 2026Decoupling Defense Strategies for Robust Image Watermarkingcited by 1
  26. 2026Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemescited by 1
  27. 2026ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Modelscited by 1
  28. 2026Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editingcited by 1
  29. 2026The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editingcited by 1
  30. 2026Learning Probabilistic Embeddings for Unsupervised Action Segmentationcited by 1
  31. 2025Deep Robust Reversible Watermarkingcited by 0
  32. 2025Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Imagescited by 0
  33. 2025SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editingcited by 0
  34. 2025Where is the Watermark? Interpretable Watermark Detection at the Block Levelcited by 0
  35. 2025WaTeRFlow: Watermark Temporal Robustness via Flow Consistencycited by 0
  36. 2026Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarkingcited by 0
  37. 2026ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarkingcited by 0
  38. 2026Whether, Which, and Whose: Solving the Triple Challenge of Deepfake Proactive Forensics in Multi-Face Scenarioscited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ONRW: Optimizing inversion noise for high-quality and robust watermark
  2. 2022Go Wide or Go Deep: Levering Watermarking Performance with Computational Cost for Specific Images ↗
  3. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Images
  4. 2025Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
  5. 2025When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
  6. 2025DINVMark: A Deep Invertible Network for Video Watermarking
  7. 2025Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal
  8. 2024Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortions