- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Approach
Generation: First, a preview image is generated, its semantic code obtained by CLIP embedding and subsequent SimHash projection. In order to embed the watermark, we return to a previous latent (e.g. at step 45, out of 50), and embed the semantic code into the frequency representation of the latent. Then we re-generate the remaining few steps but now from the watermarked latent.
Detection: the image’s semantic code is recovered by preprocessing+CLIP+SimHash. A candidate set of semantic codes is constructed that enables some tolerance to most sensitive bit flips in the semantic code. Candidate set consists of every code with at most four bit flips and every code obtained by flipping any of the 9 most uncertain semantic code bits. An expected watermark is generated for every candidate code. Note that the generated watermark patterns are independent from each other if the code differs in even one bit. In the second branch, in parallel, the image is inverted partially for a number of steps. The detection score is computed over multiple inversion steps using an alignment metric with the expected watermark. In particular, a normalized alignment score is computed for every candidate pattern against every inverted time step. The scores are averaged over the timesteps to obtain an alignment score over each candidate. The decision is then done by checking how strongly the best-matching candidate matches to the image, compared to the other candidates. If one candidate’s score is sufficiently higher than the median, the image is considered watermarked.
Preprocessing: a particularly important aspect appears to be the preprocessing, which is done to obtain more stable semantic codes. The image is copied 8 times, and on each copy, a transformation is applied (JPEG, additive noise, or blur). Then the copies are canonicalized by normalizing to mean luminance of 0.5, and by applying blur and JPEG25 compression on every image. Each preprocessed copy goes into CLIP and the CLIP embeddings are averaged before being used in semantic code construction. This is done both during generation and verification (in the semantic code branch).
Experiments are done on SD2.1-base, SD3.5 and Flux.2-klein, comparing against TreeRing, RingID, GS and PRC, and SEAL and SemBind. From the results it appears that the proposed method has high detectability, and substantially lower forgeability than SEAL and SemBind. However, it has generally lower robustness than SemBind+GS, Gaussian Shading and RingID. Ablations are provided. Without preprocessing, the robustness is poor. Interestingly, reading out only at step 45 (and not averaging over 20 inverted steps) reduces robustness, especially under Gaussian Noise.
Critical strengths
S1: interesting problem, trying to address forgeability of in-generation watermarks.
S2: reasonable approach. Reusing earlier timesteps makes sense to solve the circular dependency incurred by conditioning on image semantics. Tricks for improving robustness (preprocessing and candidate sets) appear to work.
Critical weaknesses
W1: Robustness is subpar. TPR of <99% with an FPR of 1% is not great and much lower than old baselines like RingID or GS, or SemBind+GS. TPR of 93% for Gaussian Noise is particularly weak. Improved resistance to the evaluated forgery attacks makes up for this to some degree, but still raises concerns whether the poor robustness is acceptable. For some unspecified reason, SEAL is omitted from robustness comparison.
W2: Missing ablations: There is no ablation on at what timestep the watermark is embedded, and no ablation for which steps are most important for detection (except step 45). The fact that in the last denoising steps, the reported latent estimates become highly aligned, raises the question whether we can’t simply apply the watermark on the final latent. Another important missing analysis concerns the preprocessing. The paper describes generating 8 augmented views, which are then “canonicalized” using heavy blur and jpeg compression. Given that the perturbations done before this are for a large part absorbed by canonicalization, it could be that we don’t need 8 augmented views and only need the canonicalization part on a single image. So I believe the papers needs to check for canonicalization only (no augmentations before canonicalization) as well as a few settings on the number of augmented views (1, 4, 8, 16).
W3: writing needs to be improved to improve better understanding of the paper. Also, some claims in intro aren’t correct. SemBind does not rely on prompt or caption like SEAL. Also, the paper is stating that previous methods didn’t try binding semantics and a few paragraphs later it talks about SEAL etc. The earlier claim needs to be properly scoped. Moreover, there are other presentation issues, like the non-standard placement of tables, with text wrapping around the tables (not sure this is permissible in ICLR). Also, the presentation of numbers in the tables is potentially confusing. Usually bold font is reserved for pointing out the best results in a column whereas in this paper, it simply marks the IRIS row (which is already clearly marked in blue).
Questions for authors
Q1: Why is SEAL not included in the robustness comparison?
Minor remarks: I am not sure that table formatting and their placement in the text is acceptable. Table caption is below the table.
4 comments
Response to Reviewer XFn9 [Part 2]
w2: Missing ablations: There is no ablation on at what timestep the watermark is embedded… whether we can’t simply apply the watermark on the final latent. … missing analysis concerns the preprocessing. … check for canonicalization only (no augmentations before canonicalization) as well as a few settings on the number of augmented views (1, 4, 8, 16).
We sincerely appreciate these thoughtful comments. We added ablations on the embedding timestep and the image preprocessing to the revision.
1. Ablation of watermark embedding timestep.
| embedding start step | clean (T@1%FPR) | noise 0.1 (T@1%FPR) | noise 0.1 (code recovery) | noise 0.1 (oracle pattern) | PSNR |
|---|---|---|---|---|---|
| 20 | 0.898 | 0.742 | 0.864 | 0.972 | 23.9 |
| 30 | 0.970 | 0.842 | 0.942 | 0.980 | 26.6 |
| 40 | 0.998 | 0.896 | 0.986 | 0.988 | 29.3 |
| 45 (default) | 1.000 | 0.932 | 0.982 | 1.000 | 31.3 |
| 47 | 1.000 | 0.924 | 0.990 | 0.992 | 32.5 |
| 49 (final latent) | 1.000 | 0.828 | 0.994 | 0.978 | 35.1 |
Findings: Starting the embedding later than step 45 yields a T@1%FPR of 1.0 on clean images and a higher PSNR, but lower robustness under Gaussian noise ( = 0.1).
We choose as the earliest embedding start that reaches a clean T@1%FPR of 1.0. Later starts bind the mark more tightly to the image content and give a higher PSNR, but the mark passes through fewer denoising steps and becomes less robust under noise (rows 47–49). Earlier starts lose both clean detectability and fidelity (rows 20–40).
2. Ablation of image preprocessing.
We evaluate the effectiveness of image preprocessing by examining the code recovery rate and Hamming distance of embedded and extracted semantic codes.
| Preprocessing | Metric | Q90 | Q70 | Q50 | Q30 | Q20 |
|---|---|---|---|---|---|---|
| Raw CLIP (no preprocessing) | Recovery | 0.980 | 0.914 | 0.856 | 0.742 | 0.654 |
| Raw CLIP (no preprocessing) | Hamming ↓ | 1.56 | 2.43 | 3.02 | 3.72 | 4.14 |
| Canonicalization only (no augmentation) | Recovery | 0.998 | 0.998 | 0.994 | 0.986 | 0.952 |
| Canonicalization only (no augmentation) | Hamming ↓ | 0.79 | 1.12 | 1.28 | 1.46 | 1.96 |
| Canon. + K = 1 augmented view | Recovery | 1.000 | 0.990 | 0.988 | 0.982 | 0.944 |
| Canon. + K = 1 augmented view | Hamming ↓ | 1.00 | 1.31 | 1.41 | 1.78 | 2.14 |
| Canon. + K = 4 | Recovery | 1.000 | 1.000 | 1.000 | 0.994 | 0.984 |
| Canon. + K = 4 | Hamming ↓ | 0.53 | 0.72 | 0.91 | 1.10 | 1.64 |
| Canon. + K = 8 (ours) | Recovery | 1.000 | 1.000 | 1.000 | 1.000 | 0.996 |
| Canon. + K = 8 (ours) | Hamming ↓ | 0.37 | 0.62 | 0.80 | 0.95 | 1.54 |
| Canon. + K = 16 | Recovery | 1.000 | 1.000 | 0.998 | 1.000 | 0.988 |
| Canon. + K = 16 | Hamming ↓ | 0.29 | 0.49 | 0.71 | 0.85 | 1.48 |
Findings: Canonicalization alone effectively increases code recovery rate and reduces Hamming distance. Averaging over augmented views further improves these two metrics under JPEG compression. A single random view (K = 1) is slightly worse than canonicalization alone, because one random augmentation adds variance that is only averaged out with several views.
Response to Reviewer XFn9 [Part 3]
W3 & remarks: writing needs to be improved to improve better understanding of the paper. Also, some claims in intro aren’t correct. SemBind does not rely on prompt or caption like SEAL. Also, the paper is stating that previous methods didn’t try binding semantics and a few paragraphs later it talks about SEAL etc. The earlier claim needs to be properly scoped. Moreover, there are other presentation issues, like the non-standard placement of tables, with text wrapping around the tables (not sure this is permissible in ICLR). Also, the presentation of numbers in the tables is potentially confusing. Usually bold font is reserved for pointing out the best results in a column whereas in this paper, it simply marks the IRIS row (which is already clearly marked in blue).
We sincerely thank you for these careful questions and comments that help us improve this paper. We clarify that SemBind uses a prompt-conditioned corpus to train its semantic code extractor. We have revised the claim in the introduction and fixed the issues in table and data presentation in the revision.
1. SemBind’s semantic binding is prompt-level. The reviewer is right that SemBind does not take the prompt or a caption as input: its semantic masker operates on the embedding of an auxiliary generated image. Our description “prompt-level” refers to the granularity of the binding, not the input. The masker of SemBind is trained with contrastive learning on a large prompt-conditioned corpus so that it yields "near-invariant codes for the same prompt and near-orthogonal codes across prompts" [1, Abstract and Sec. 3.1]. The watermark is therefore bound to the prompt-level cluster that an image belongs to. To avoid this misreading, we have clarified the introduction: it now states that SemBind derives its code from an auxiliary image’s embedding trained for prompt-level clustering, and we removed the sentence “The prompt is the only image-related quantity available before generation starts, so the binding is forced to stop there.”
[1] Zhang, Xin, et al. “SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks.” Forty-third International Conference on Machine Learning. 2026.
2. Scope of the claim in the introduction. We agree that the claim was not properly scoped. The second paragraph of the introduction stated that “existing in-generation watermarking methods” are content-agnostic. In contrast, the third paragraph then introduced SEAL and SemBind as methods that do bind the watermark to semantics. We have revised the second paragraph so that the content-agnostic claim applies only to the methods it describes: it now reads “most existing in-generation watermarking methods, such as Tree-Ring and Gaussian Shading, … embed content-independent marks in the initial noise”, and attributes their vulnerability to the fact that “their watermarks are agnostic to the content”. The third paragraph then positions SEAL and SemBind as content-aware methods whose binding is loose because the semantics come from an auxiliary image, which is the limitation IRIS addresses.
3. Presentation. We replaced the wrapped tables with standard floating tables with titles above, and we removed the bold font from the IRIS rows. Bold now marks the best value in each column, and the IRIS row is highlighted only by the colored background.
Best regards,
The Authors
Final Request for Feedback Before the Discussion Closes
Dear Reviewer XFn9,
With less than three hours remaining in the discussion period, we sincerely ask you to take a final look at our rebuttal.
We have carefully addressed your concerns through additional robustness evaluations, comprehensive ablation studies on embedding timing and preprocessing, and substantial improvements to the manuscript's writing and presentation.
Despite our previous reminders, we have not yet received your feedback. We would be extremely grateful if you could briefly confirm whether our responses have addressed your concerns and reconsider your assessment accordingly.
We sincerely hope to have the opportunity to hear from you before the discussion closes.
Thank you very much for your time and consideration.
Best regards,
The Authors
Response to Reviewer XFn9 [Part 1]
We sincerely thank Reviewer XFn9 for providing these thoughtful comments and questions.
We would like to note that IRIS improves over both content-aware and content-agnostic methods. Compared to content-aware methods, IRIS pays a smaller cost in robustness for a significant gain in forgery resistance. Compared to content-agnostic methods, IRIS achieves comparable detectability when using a key-only pattern and maintains improved visual fidelity (the watermarked image stays visually identical to the unwatermarked image).
1. IRIS achieves an improved trade-off between robustness to distortions and resistance to watermark transplantation. The table below reports the average T@1%FPR over the seven distortions in Section 5.2, Table 2 and and the 1−Forgery ASR from Section 5.2, Table 1. The last column reports the worst of the two. Relative to SemBind+GS, IRIS gives up 2.2 points of distortion robustness and gains 43.8 points of forgery resistance.
2. The oracle mark detectability of IRIS achieves robustness approaching that of RingID and GS. As shown in Section 5.2, Table 2, IRIS oracle pattern detection rates (T@1%F) are 0.99–1.0. In our response to Reviewer 2DoM, when evaluating WAVES removal attacks, IRIS without semantic binding also achieves robustness comparable to GS and RingID. We note that IRIS achieves this robust oracle mark detectability while maintaining high visual fidelity, which GS and RingID do not.
3. Robustness comparison with SEAL. We evaluated SEAL under the same protocol as the other baselines in Table 2, but we omitted its row by oversight. We have added this row to Table 2 in the revision. SEAL is less robust than IRIS under every distortion.