mlsanityData to 14 Oct 2026

InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance

arXiv 2411.07795 ↗First posted 10 Nov 2024cs.CR cs.AIcited by 23

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

Abstract (arXiv)

The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR~51, SSIM ~ 0.998) while maintaining over 97% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, significantly expanding payload capacity while preserving image quality. This enables the embedding of UUIDs with error correction codes, achieving near-perfect decoding success rates even under challenging image distortions. We also address potential vulnerabilities against advanced attacks and propose mitigation strategies. By combining high imperceptibility, extended payload capacity, and resilience to manipulations, InvisMark provides a robust foundation for ensuring media provenance in an era of increasingly sophisticated AI-generated content. Source code of this paper is available at: https://github.com/microsoft/InvisMark.

Key facts. Cited by 23 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 20 of its 42 references that are in the map. First posted on arXiv 10 Nov 2024.

Builds on

20 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks29 Sep
  2. 2023Invisible Image Watermarks Are Provably Removable Using Generative AI2 Jun
  3. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators14 Apr
  4. 2023RoSteALS: Robust Steganography using Autoencoder Latent Space6 Apr

Other references · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  6. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  7. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  8. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  9. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 206
  10. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  11. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  12. 2021Watermarking Images in Self-Supervised Latent Spacescited by 94
4 more
  1. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 52
  2. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 51
  3. 2023GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Modelscited by 42
  4. 2021VPN: Video Provenance Network for Robust Content Attributioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 15.

23 papers.

Sort:

By area:

  1. 2025SynthID-Image: Image watermarking at internet scalecited by 31
  2. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 15
  3. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 12
  4. 2025MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Modelscited by 6
  5. 2025Guidance Watermarking for Diffusion Modelscited by 5
  6. 2026Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflectioncited by 3
  7. 2026Learning to Watermark in the Latent Space of Generative Modelscited by 3
  8. 2026All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermarkcited by 2
  9. 2025MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarkscited by 1
  10. 2025Low-Compute Watermark Removal via Dual-Domain Natural Projectioncited by 1
  11. 2026Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removalcited by 1
  12. 2026Compositional Adversarial Training for Robust Visual Watermarkingcited by 1
11 more
  1. 2026Learning Probabilistic Embeddings for Unsupervised Action Segmentationcited by 1
  2. 2025MultiNeRF: Multiple Watermark Embedding for Neural Radiance Fieldscited by 0
  3. 2026Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarkingcited by 0
  4. 2026ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarkingcited by 0
  5. 2026Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generationcited by 0
  6. 2026DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authenticationcited by 0
  7. 2026Beyond AI-Generated Labels: Watermarking, Co-Creation, and Conflation of AI-Generation with Disinformationcited by 0
  8. 2026Signpost Watermarking: Joint Optimization for Visual Watermark Coexistencecited by 0
  9. 2026Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenancecited by 0
  10. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0
  11. 2026WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
  2. 2025Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
  3. 2025IConMark: Robust Interpretable Concept-Based Watermark For AI Images
  4. 2026SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding
  5. 2025WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
  6. 2026FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
  7. 2023Evading Watermark based Detection of AI-Generated Content
  8. 2024Invisible Watermarks: Attacks and Robustness