mlsanityData to 7 Oct 2026

Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images

arXiv 2604.19090 ↗First posted 21 Apr 2026cs.CRcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Existing single-domain watermarking methods either fail under regeneration, remain vulnerable to black-box reprompting that enables adversarial framing, or provide no spatial evidence for tampered regions. We propose Dual-Guard, a dual-channel latent watermarking framework for practical provenance verification, framing resistance, and region-level tamper localization. Dual-Guard combines two complementary anchors: a Gaussian Shading watermark in the initial diffusion noise as a global provenance signal, and a Latent Fingerprint Codec in the final denoised latent as a structured content anchor. Reprompting tends to preserve the former while breaking the latter, whereas localized edits disturb the content anchor only in tampered regions. In Full mode on a 2,400-sample benchmark, Dual-Guard keeps clean-image authentication false rejection and tamper false alarm below one half of one percent, while maintaining near-complete detection under reprompting, diffusion editing, and eight local tampering attacks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 21 of its 35 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

21 of 35 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models4 Dec
  2. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  3. 2023A Recipe for Watermarking Diffusion Models17 Mar

Other references · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  6. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  7. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  8. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  9. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  10. 2021MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detectioncited by 117
  11. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
  12. 2021Watermarking Images in Self-Supervised Latent Spacescited by 90
6 more
  1. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  2. 2020Distortion Agnostic Deep Watermarkingcited by 88
  3. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  4. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attackscited by 75
  5. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  6. 2025SEAL: Semantic Aware Image Watermarkingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecyclecited by 0
  2. 2026Representation Learning in Diffusion and Flow-based Model: An Application Aspectcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization
  2. 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
  3. 2025SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
  4. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space
  5. 2026Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
  6. 2026SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
  7. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking
  8. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models