- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2(+1)
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This manuscript proposes EraseForge, a no-box watermark forgery attack that leverages diffusion-based watermark removal to construct proxy training data and trains a conditional diffusion model to generate watermark residuals. The proposed method achieves competitive forgery performance with fewer training samples than existing approaches. The authors further introduce two defense mechanisms, SeedBind and ContentBind, which aim to prevent forgery through message consistency verification and content-dependent watermark generation.
Critical strengths
-
The focused problem that investigating watermark forgery attacks under the practical no-box setting is an important security concern for AI-generated content attribution.
-
The authors evaluate the proposed attack across multiple watermarking schemes and datasets. The experiments are sufficient.
Critical weaknesses
-
My major concern is that the proposed EraseForge framework largely combines existing techniques, including diffusion-based watermark removal, watermark residual extraction, and conditional diffusion modeling. Prior works such as WMCopier and WMForger have already explored diffusion-based watermark forgery and residual-based attacks. The proposed conditional residual modeling appears to be a relatively straightforward extension of these established techniques, offering limited novelty for a top-tier conference like ICLR.
-
Both SeedBind and ContentBind rely on well-established concepts in watermarking and authentication (e.g., Weng et al. (2012), Robust Image Content Authentication Using Perceptual Hashing and Watermarking). SeedBind essentially introduces deterministic consistency checks between message components, while ContentBind binds watermark messages to image features through perceptual hashing. Similar principles have been extensively studied in content-dependent watermarking and image authentication.
-
In the manuscript, the authors repeatedly emphasize a 5× improvement in data efficiency by reducing training samples from 5,000 to 1,000. However, both dataset sizes are relatively small, and such a reduction may not provide a substantial practical advantage. Furthermore, the proposed approach involves multiple computationally expensive stages, including diffusion-based removal, training, and refinement. Without comparing end-to-end computational costs, the practical significance of this improvement remains unclear.
-
Some latest relevant recent research are overlooked, such as Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering (AAAI 2026). Although this work focuses on watermark removal rather than forgery, it also exploits the additive properties of watermark signals and uses surrogate modeling.
Questions for authors
See weaknesses. I may modify my rating based on the authors' rebuttal.
6 comments
[CW #1] Novelty of EraseForge relative to WMCopier / WMForger. We thank the reviewer for raising this concern, and we have improved our write-up to explain the novelty and contribution of EraseForge more clearly. EraseForge builds on known components, but it is not a straightforward extension of either prior attack, which belong to different families:
- WMForger is a residual-copy attack. It extracts the watermark residual of a single image by optimisation against an image-preference model, then pastes that fixed residual onto target images. Nothing is learned about the watermark.
- WMCopier and EraseForge are estimator-based, but they solve different learning problems.
- WMCopier models the distribution of watermarked images, so the watermark must be learned jointly with image content.
- EraseForge uses diffusion-based removal to construct proxy (clean, watermarked) pairs. This turns no-box forgery into supervised conditional residual estimation of p(δ | x), learning only the watermark signal conditioned on the target content.
| WMForger | WMCopier | EraseForge | |
|---|---|---|---|
| Family | residual copy | estimator | estimator |
| What is learned | nothing (one residual extracted per image) | distribution of watermarked images | conditional distribution of the watermark residual given content |
| Training signal | — | watermarked images only | removal-generated proxy pairs (x_r, x_w) |
| Data | 1 image | 5k–50k | 1k (single message); 20k breaks a 100-message pool |
This reformulation, not the individual components, is what produces the gains we report. Each claim is supported by an experiment:
- Less data. Comparable forgery with 5× fewer samples (Table 1).
- A changed security conclusion.
- WMCopier reported that a K=100 message pool withstands forgery even with 50k samples.
- In our evaluation, WMCopier stays at 69–72% bit accuracy (Table 3), while EraseForge exceeds 91% at N=20k.
- The multi-message strategy, the main existing forgery defense, is therefore insufficient.
- Both parts of the formulation are necessary.
-
Residual target: residual vs. full-image modelling gives an 8–10 dB PSNR gain at comparable or better bit accuracy (Table 8).
-
Conditional generation (new, also requested by Reviewer P9gr): a direct residual regressor uses the same UNet, proxy pairs and training budget, and is trained with MSE in a single forward pass. HiDDeN-48, N=1k; forged bit accuracy / PSNR:
single message 10-message pool EraseForge (conditional diffusion) 99.2% / 31.8 dB 81.6% / 32.0 dB Direct residual regressor (same pairs) 98.2% / 29.0 dB 73.2% / 27.6 dB If EraseForge were a straightforward extension, residual regression on the proxy pairs would suffice. It does for a single message, but not once the defender uses multiple messages.
-
Changes in the revised paper (marked in blue).
- Contributions (§1, L. 105). The first contribution now states the novelty explicitly: "We introduce EraseForge, which reformulates no-box watermark forgery as supervised conditional residual estimation: diffusion-based watermark removal constructs proxy (clean, watermarked) pairs, from which a conditional diffusion model learns the distribution of the watermark residual given the target image."
- Introduction (§1, L. 85). A new paragraph explains how EraseForge differs from WMForger and WMCopier, and why both the residual target (Table 8) and conditional generation (Appendix B.5) are necessary.
- Related Work (§6, Watermark Attacks, L. 505). New sentences position EraseForge within the estimator family and point to the comparison table above, now Table 6 in Appendix A.4 (L. 952).
- New ablation (Appendix B.5, L. 1121). The comparison with a direct residual regressor trained on the same pairs (point 3 above; also requested by Reviewer P9gr).
[CW #2] Relation of SeedBind / ContentBind to prior authentication work. We thank the reviewer for pointing us to this line of work. ContentBind and SeedBind share a similar idea with Weng et al. (2012): verification information is embedded in the watermark itself, so that the verifier can re-derive it and check it. ContentBind in particular, like Weng et al., embeds a hash derived from the image. However, our approaches differ from theirs in the threat model, the components and the security analysis, as summarised below. We developed SeedBind and ContentBind independently and were not aware of this prior work at the time. We have added it to the Related Work section and acknowledge it explicitly (§6, L. 517).
Weng et al. (PCM 2012) address content authentication along a distribution chain:
- A keyed perceptual hash is embedded in the same image with a robust STDM watermark placed in different wavelet subbands, so that embedding does not disturb the hash. The hash consists of sign bits of low-frequency DCT coefficients of a wavelet approximation band, permuted with a secret key.
- The verifier extracts the embedded hash, recomputes the hash from the received image, and accepts if their Hamming distance is below a threshold. This distinguishes incidental distortion from malicious tampering.
- The idea goes back to Fridrich (1999) and Fridrich & Goljan (2000), who proposed image-dependent watermarks, which counter attacks that copy a watermark between images such as the copy attack of Kutter et al. (2000).
The differences between Weng et al. (2012) and our approaches are as follows:
| Weng et al. 2012 (and Fridrich & Goljan) | ContentBind (ours) | SeedBind (ours) | |
|---|---|---|---|
| Goal / threat | integrity: detect tampering of a given image | provenance: detect transplanting a provider's watermark onto other content (false attribution) | provenance against learned estimators |
| Adversary evaluated | content editing; no learning adversary | learned forgers: one-shot residual copying (WMForger) and diffusion-based estimation (EraseForge) | EraseForge |
| Binding | keyed perceptual hash of the same image | secret projection of learned features (DINOv2) | internal seed–hash consistency, independent of content |
| Watermark | hand-designed STDM, co-designed with the hash | off-the-shelf neural watermarkers, unmodified | same |
| Security analysis | collision probability of the hash | learnability of the binding by a data-driven attacker | sensitivity of the consistency check to decoding errors |
Changes in the revised paper (marked in blue).
- Related Work (§6, Forgery Defense, L. 517). We credit Fridrich (1999), Fridrich & Goljan (2000), the copy attack of Kutter et al. (2000), Lin & Chang (2001), Weng et al. (2012) and Swaminathan et al. (2006), and state that SeedBind and ContentBind adapt these binding principles to off-the-shelf neural watermarks and evaluate them against learned forgers.
- §5.1, SeedBind (L. 374). SeedBind is described as a self-authenticating payload, in which part of the message is a deterministic function of the rest.
- §5.1, ContentBind (L. 430). ContentBind is described as following the classical principle of content-dependent watermarking (Fridrich & Goljan, 2000; Weng et al., 2012).
- New Appendix D.5, "Relation to Content Authentication" (Table 14, L. 1297). The comparison table above.
We sincerely thank the reviewer for the thoughtful critique and for acknowledging the contributions of our work:
We also thank the reviewer for being open to revising their assessment, and we address each concern below.
Summary
Section, table and line numbers below refer to the revised manuscript; all changes are marked in blue.
Based on the reviewer's feedback, we have made the following changes:
The end-to-end computational cost requested in CW #3 is reported in this response.