mlsanityData to 14 Oct 2026

Your Text Encoder Can Be An Object-Level Watermarking Controller

arXiv 2503.11945 ↗First posted 15 Mar 2025cs.CV cs.CR cs.LGcited by 1

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

Abstract (arXiv)

Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings W_*, we enable watermarking in selected objects or parts of the image, offering greater flexibility compared to traditional full-image watermarking. Our method leverages the text encoder's compatibility across various LDMs, allowing plug-and-play integration for different LDMs. Moreover, introducing the watermark early in the encoding stage improves robustness to adversarial perturbations in later stages of the pipeline. Our approach achieves 99% bit accuracy (48 bits) with a 105 × reduction in model parameters, enabling efficient watermarking.

Key facts. Cited by 1 paper 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 26 of its 41 references that are in the map. First posted on arXiv 15 Mar 2025.

Builds on

26 of 41 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024LaWa: Using Latent Space for In-Generation Image Watermarking11 Aug
  2. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA18 May
  3. 2024A Watermark-Conditioned Diffusion Model for IP Protection16 Mar
  4. 2023Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking12 Sep
  5. 2023Invisible Image Watermarks Are Provably Removable Using Generative AI2 Jun
  6. 2023RoSteALS: Robust Steganography using Autoencoder Latent Space6 Apr
  7. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar

Other references · 19

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  5. 2022Diffusion Models for Adversarial Purificationcited by 476
  6. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  7. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 310
  8. 2022Inversion-Based Style Transfer with Diffusion Modelscited by 291
  9. 2022Soft Diffusion: Score Matching for General Corruptionscited by 102
  10. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Modelscited by 100
  11. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 97
  12. 2021A survey of deep neural network watermarking techniquescited by 73
7 more
  1. 2024Watermark Anything with Localized Messagescited by 53
  2. 2024RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlcited by 48
  3. 2023Scene-Conditional 3D Object Stylization and Compositioncited by 4
  4. 2019Perception-oriented Single Image Super-Resolution via Dual Relativistic Average Generative Adversarial Networkscited by 2
  5. 2024Survival Analysis of Young Triple-Negative Breast Cancer Patientscited by 2
  6. 2024SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attackscited by 2
  7. 2025Exploring Iterative Manifold Constraint for Zero-shot Image Editingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Score-Control for Hallucination Reduction in Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
  2. 2025SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
  3. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models
  4. 2025TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
  5. 2024SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
  6. 2026Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
  7. 2025Image Watermarking of Generative Diffusion Models
  8. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Models