Lune

ICCV2025Top-tier venue

SEAL: Semantic Aware Image Watermarking

Kasra Arabi, R. Teal Witter, Chinmay Hegde, Niv Cohen

Abstract

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques to mark synthetic images. Watermarks are typically expected to preserve the integrity of the target image, withstand removal attempts, and prevent unauthorized insertion of the watermark pattern onto unrelated images. To address this need, recent methods embed persistent watermarks into images produced by diffusion models using the initial noise of the diffusion process. Yet, to do so, they either distort the distribution of generated images or require searching a large dictionary of candidate noise patterns for detection.

In this paper, we propose a novel watermarking method that embeds semantic information about the generated image into the noise pattern, enabling a distortion-free watermark that can be verified without requiring a database of key patterns. Instead, the key pattern can be inferred from the semantic embedding of the image using locality-sensitive hashing. Furthermore, conditioning the watermark detection on the original image content improves its robustness against forgery attacks. To demonstrate that, we consider two largely overlooked attack strategies: (i) an attacker extracting the initial noise and generating a novel image with the same pattern; (ii) an attacker inserting an unrelated (potentially harmful) object into a watermarked image, while preserving the watermark. We empirically validate our method's increased robustness to these attacks. Taken together, our results suggest that content-aware watermarks can mitigate risks arising from image-generative models. Our code is available at https://github.com/Kasraarabi/ SEAL.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • The Stable Signature: Rooting Watermarks in Latent Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • GROW: Watermark Generation with Progressive Guidance for Diffusion Models cites The Stable Signature: Rooting Watermarks in Latent Diffusion Models
  • GROW: Watermark Generation with Progressive Guidance for Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • GROW: Watermark Generation with Progressive Guidance for Diffusion Models cites Directly Denoising Diffusion Models
  • Directly Denoising Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Invisible Image Watermarks Are Provably Removable Using Generative AI cites The Stable Signature: Rooting Watermarks in Latent Diffusion Models
  • Invisible Image Watermarks Are Provably Removable Using Generative AI cites High-Resolution Image Synthesis with Latent Diffusion Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. GROW: Watermark Generation with Progressive Guidance for Diffusion ModelsPengcheng Luo, Zexi Jia, Yijia Zhong, Jinchao Zhang et al.CVPR 2026

Builds on14

  1. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  2. Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
  3. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
  4. The Stable Signature: Rooting Watermarks in Latent Diffusion ModelsPierre Fernandez, Guillaume Couairon, Hervé Jégou, Matthijs Douze et al.ICCV 2023 · 370 citations
  5. Invisible Image Watermarks Are Provably Removable Using Generative AIXuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan et al.NeurIPS 2024 · 209 citations

Related papers

  1. Hidden in the Noise: Two-Stage Robust Watermarking for ImagesKasra Arabi, Benjamin Feuer, R. Teal Witter, Chinmay Hegde et al.ICLR 2025
  2. Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion ModelsWenda Li, Huijie Zhang, Qing QuNeurIPS 2025 · 8 citations
  3. Black-Box Forgery Attacks on Semantic Watermarks for Diffusion ModelsAndreas Müller, Denis Lukovnikov, Jonas Thietke, Asja Fischer et al.CVPR 2025
  4. Tree-Rings Watermarks: Invisible Fingerprints for Diffusion ImagesYuxin Wen, John Kirchenbauer, Jonas Geiping, Tom GoldsteinNeurIPS 2023 · 253 citations
  5. RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable GuaranteesXun Xian, Ganghua Wang, Xuan Bi, Jayanth Srinivasa et al.NeurIPS 2024 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines