- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes a watermark for diffusion models that is tied to the image it marks, so that a watermark copied from one image should not verify on another. A few denoising steps before generation ends, the model's prediction of the final image already shows its coarse layout. The method turns this layout into a short binary code. It combines this code with a secret key to decide the watermark pattern added in the remaining denoising steps, and for detection it recomputes the code from the received image. The authors prove an upper bound on forgery success that depends mainly on the chance that a forged image shares a code with a watermarked image.
Critical strengths
- Against the attacks the paper tests, the method's worst-case robustness to forgery is higher than that of all baselines.
- Unlike SemBind, the method does not generate an extra image or use a separate model to embed the watermark into the image.
Critical weaknesses
- The method can fail if the forger copies the watermark from a watermarked image with a similar coarse layout, and the paper does not test such an attack. In one of the tested attacks, every forgery whose layout happened to match passed verification (Table 10).
- A forger could also take a watermarked image and change its content, for example by inpainting a different object into one region. Because the watermark is tied only to coarse layout, it may still verify, and the paper does not test such edits.
- Close baselines are missing, including CSGuard [1], SEAL [2], and WIND [3].
References
[1] Jiewei Lai, Lan Zhang, Chen Tang, Pengcheng Sun, Zhaopeng Zhang, Yunhao Wang, and Hui Jin. CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint. arXiv:2605.01479, 2026.
[2] Kasra Arabi, R. Teal Witter, Chinmay Hegde, and Niv Cohen. SEAL: Semantic Aware Image Watermarking. ICCV 2025.
[3] Kasra Arabi, Benjamin Feuer, R. Teal Witter, Chinmay Hegde, and Niv Cohen. Hidden in the Noise: Two-Stage Robust Watermarking for Images. ICLR 2025.
Questions for authors
- Suppose an attacker wants to forge the watermark into an image. They collect many watermarked images, say 1,000 to 100,000, pick the one whose coarse layout is closest to their image, and possibly nudge their image's layout toward it. How often does copying that image's watermark onto their image then pass verification?
- If a watermarked image is edited by inpainting one region, or by regenerating it with a changed prompt, does its watermark still verify?
- How many forged images are used for each forgery result?
6 comments
Response to Reviewer y87a (2/3): Inpainting and Changed-Prompt Regeneration (W2/Q2)
For W2/Q2, the attacker edits a genuine watermarked image and attempts to retain valid evidence for the altered content. The edits use public models or region replacement, with the region, prompt and random seed fixed independently of verification results. The attacker has no access to the secret key, private content-code parameters or verifier, following the threat model in Sec. 3.2. We apply the deployed receiver only after saving the edits, to measure detection and exact-message success.
Q2/W2. Inpainting and regeneration with a changed prompt. We added this result in Section F.7 "Robustness to Inpainting and Regeneration with A Changed Prompt" in the revised submission (Appendix, Lines 2092–2113, Tab. 14).
We evaluated 300 genuine watermarked images per dataset and variant on MS-COCO, DiffusionDB and DALL-E 3. We tested the following editing techniques:
- Inpainting: We use the Diffusers inpainting pipeline [1] with Stable Diffusion 2 to repaint a rectangular region covering 50% of the image using an object prompt. We preserve all pixels outside the rectangle.
- Region replacement: We replace the same rectangle with the corresponding region from another image's unwatermarked companion, again preserving all pixels outside the rectangle.
- Img2img with a changed prompt: We use SD 2.1-base with a mismatched caption and denoising strength 0.7. The Diffusers pipeline [2] implements SDEdit's noise-and-denoise procedure [3], conditioned here on the new prompt.
Each entry is Min / Opt. Lower is better.
| Technique | Strength | MS-COCO | MS-COCO | DiffusionDB | DiffusionDB | DALL-E 3 | DALL-E 3 |
|---|---|---|---|---|---|---|---|
| Inpainting | 50% area | 0.170 / 0.156 | 0.016 / 0.013 | 0.180 / 0.183 | 0.037 / 0.023 | 0.160 / 0.146 | 0.007 / 0.013 |
| Region replacement | 50% area | 0.047 / 0.050 | 0.004 / 0.009 | 0.083 / 0.080 | 0.010 / 0.020 | 0.077 / 0.070 | 0.000 / 0.003 |
| Img2img, changed prompt | 0.7 | 0.117 / 0.123 | 0.000 / 0.000 | 0.156 / 0.130 | 0.000 / 0.000 | 0.117 / 0.107 | 0.000 / 0.000 |
Results. TrajBind achieves strong forgery resistance across all three datasets and both variants, including edits covering half of the image. It rejects most detection-level forgery attempts and prevents exact-message forgery in at least 96.3% of cases, including all tested changed-prompt regenerations. For 50% region edits, detection-level success is 14.6–18.3% for inpainting and 4.7–8.3% for region replacement; changed-prompt regeneration at strength 0.7 reaches 10.7–15.6% detection-level success and zero exact-message success.
[1] Hugging Face. Inpainting. Diffusers documentation. Retrieved November 9, 2026.
[2] Hugging Face. Image-to-image. Diffusers documentation. Retrieved November 9, 2026.
[3] C. Meng, Y. He, Y. Song, J. Song, J. Wu, J.-Y. Zhu, and S. Ermon. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. International Conference on Learning Representations (ICLR), 2022.
Response to Reviewer y87a (3/3): Comparison with CSGuard, SEAL, and WIND (W3) and Sample Counts (Q3)
W3. Comparison with CSGuard, SEAL, and WIND. We added this result in Section F.6 "Additional Comparisons with SEAL and WIND" in the revised submission (Appendix, Lines 2068–2090, Tab. 13). The main paper points to it in Sec. 5 (Lines 384–385).
WIND [5] and SEAL [6] are now evaluated directly. We use 1,000 watermarked images on the MS-COCO dataset and the five forgery attacks of Sec. 5.1. The reported metric is (lower is better):
| Method | Averaging | Latent-Matching | Imprinting | Reprompting | WMCopier |
|---|---|---|---|---|---|
| WIND | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| SEAL | 0.817 | 0.040 | 0.100 | 0.750 | 0.100 |
| TrajBind-Opt | 0.000 | 0.000 | 0.000 | 0.003 | 0.000 |
Results. TrajBind-Opt achieves stronger robustness than both SEAL and WIND under every evaluated forgery attack. WIND accepts all tested forgeries, and SEAL remains particularly vulnerable to Averaging and Reprompting. TrajBind-Opt successfully rejects all tested forgeries under four attacks and 99.7% under Reprompting.
We could not locate a publicly available official implementation of CSGuard [4], so we restrict our comparison with TrajBind to their conceptual differences (which we already compared in our submission). To clarify, we revised Section "Content-Bound Watermark Methods" (App. B.1, Lines 1128–1143): CSGuard's Appendix A.4.4 reports 93.75% Reprompting attack success when both the attacker and target use SD 2.1, compared with 28.12% when an SD 2.1 attacker targets SDXL. These results show that its reported forgery resistance depends on the attacker–target model pairing. The design also differs: CSGuard constrains the denoising and inversion trajectories through a secret compressed-sensing matrix while retaining content-independent watermark bits, whereas in TrajBind the content code selects the keyed signed permutation and enters the polar encoding, so both detection and exact-message decoding depend on the content.
Q3. Number of forged images per result. 1,000 prompts per dataset per forgery attack (Sec. 5.1, Line 394), which are clearly stated in the paper. The experiments added in this rebuttal use 100 target images per dataset for the coarse-layout attack (Sec. 5.2, App. F.5), 1,000 watermarked images for SEAL and WIND (App. F.6), and 300 genuine watermarked images per dataset and variant for the editing attacks (App. F.7).
[4] J. Lai, L. Zhang, C. Tang, P. Sun, Z. Zhang, Y. Wang, and H. Jin. CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint. arXiv:2605.01479, 2026.
[5] K. Arabi, B. Feuer, R. T. Witter, C. Hegde, and N. Cohen. Hidden in the Noise: Two-Stage Robust Watermarking for Images. International Conference on Learning Representations (ICLR), 2025.
[6] K. Arabi, R. T. Witter, C. Hegde, and N. Cohen. SEAL: Semantic Aware Image Watermarking. IEEE/CVF International Conference on Computer Vision (ICCV), pp. 16196–16205, 2025.
Response to Reviewer y87a (1/3): Threat Model and Coarse-Layout Forgery (W1/Q1)
We thank the reviewer for taking the time to review our submission. We address each weakness and question point by point below. All line, table, section, and appendix numbers refer to the revised PDF unless stated otherwise. We first clarify the motivation and the threat model defined in our work, then report the requested experimental results.
TrajBind addresses black-box watermark forgery under Sec. 3.2 and App. D. An adversary transfers watermark evidence from genuine images to a chosen target while preserving the target's appearance and meaning, as required by Sec. 3.1. The motivating threat is false attribution of malicious content to a legitimate provider or user. The adversary may use the public diffusion backbone and optimize surrogate models, while the secret key, content-code parameters and verifier remain private (Sec. 3.2, Lines 139–143). We have clarified these restrictions in the revised submission in Sec. 3.1 (Lines 111–126).
For W1/Q1, to ensure the requested attack lies within our defined threat model, our reference selection and gradient updates use public features, with no private content-code parameters or verifier feedback. The objective matches the selected reference's content features and watermark signal, with an LPIPS penalty to limit perceptual changes to the target.
Q1/W1. We added this result in Section 5.2 "Robustness to Coarse-Layout Forgery Attack" (Main paper, Lines 406–428, Tab. 2) and Section F.5 "Coarse-Layout Comparison with SemBind" in the revised submission (Appendix, Lines 2041–2065, Tab. 12).
Coarse-layout experiment. We used 100 target images and 2,000 watermarked references per dataset and variant on MS-COCO, DiffusionDB and DALL-E 3. This pool size lies within the 1,000 to 100,000 range the reviewer suggested; the limited rebuttal period prevented us from scaling this experiment to 100,000 watermarked references. Each entry is Min / Opt.
The first two columns count a target as successful if any tested attack output passes detection (ASRdet) or recovers the full payload (ASRmsg), without filtering by LPIPS. They therefore include successful outputs even when the attack substantially changes the target's appearance. The last column counts detection successes only when the accepted output has LPIPS ≤ 0.10, which limits its perceptual difference from the original target (Eq. 2). At LPIPS ≤ 0.10, TrajBind successfully prevents watermark forgery on 93–96% of target images across all three datasets and both variants, even when the attacker selects a watermarked reference with a similar layout.
Comparison with SemBind. We used 100 target images per dataset and method on MS-COCO and DALL-E 3. Each method uses 2,000 watermarked references per dataset. The table reports ASRdet (Tab. 12).
Results. TrajBind-Opt achieves stronger robustness than the state-of-the-art SemBind against this layout-based forgery attack across all evaluated settings on both datasets. At LPIPS ≤ 0.10, our ASRdet is 4% on MS-COCO and 6% on DALL-E 3, compared with 50% and 81–82% for SemBind, respectively. TrajBind strengthens forgery resistance by combining the secret key with a content code extracted within the image's own generation trajectory to determine the watermark pattern. Verification checks this pattern against candidate codes derived from the received image, so matching a reference's coarse layout or public features alone does not ensure successful watermark transfer.
Table 10 and the requested coarse-layout experiment serve different purposes. Table 10 of the original submission is Tab. 11 in the revised PDF (App. F.4, Lines 1998–2039). There, we use private system access to identify content-code collisions and examine their relationship with forgery success, providing empirical support for our theoretical analysis. This private access exceeds the capabilities granted to the adversary in our threat model and is used only by us as evaluators. The coarse-layout experiment requested by the reviewer tests an attack that selects a similar watermarked reference and modifies the target using public features.