- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
PreFix aims to improve the robustness of inversion-based generative image watermarking against geometric and non-geometric distortions. It first learns a shared template and an alignment predictor, then optimizes an additive residual for each image before release. The optimization accounts for sampled non-geometric distortions, while the alignment predictor corrects geometric transformations before inversion. The evaluation covers four watermarking methods on SD-v1.4 and SD-v2.1, with additional GS results on SDXL and SD-v3.
Critical strengths
-
The reported robustness gains are substantial across several watermarking methods and generative models. For GS on SD-v2.1, geometric bit accuracy increases from 0.502 to 0.944. The experiments across different distortion strengths and the component ablations help clarify the effects of the proposed method.
-
The study of the optimization budget for each image is useful. In particular, the template and alignment configuration without refinement for each image () already achieves 0.923 geometric bit accuracy for GS (Table 7). This result helps distinguish the contribution of alignment from the additional improvement obtained through residual optimization. The reported computational costs also make this comparison relevant to practical use.
Critical weaknesses
1.The novelty of PreFix is not sufficiently clear. SynTag [1] has already studied geometric robustness in inversion based image watermarking using synchronization and geometric correction. The paper should explain more clearly how PreFix differs from this work. Table 7 also raises a question about the benefit of the proposed optimization. For GS, using the shared template and alignment predictor without further optimization already improves geometric bit accuracy from 0.502 to 0.923. The full method reaches 0.944, but generation time increases from 7.29 s to 28.14 s. The additional benefit of optimizing the residual for each image therefore seems limited for geometric robustness, given the extra cost.
2.Some important implementation details are missing. Equation (7) defines the optimization objective, but it is unclear how the extraction loss and its gradients are handled for GS and PRC. The paper also does not report the loss weights or the numerical fidelity constraint. These details are important for reproducing the method and understanding how much image distortion is introduced to improve robustness.
Reference [1] "SynTag: Enhancing the Geometric Robustness of Inversion-based Generative Image Watermarking." ICCV, 2025.
Questions for authors
-
How does PreFix compare with SynTag under comparable watermark payloads, detection operating points, and image fidelity? Could the authors also distinguish the contribution of the shared template and alignment from that of residual optimization for each image?
-
What differentiable objective is optimized for each watermarking method? Please clarify the losses specific to each method, loss weights, distortion sampling procedure, and gradient treatment of watermark extraction, JPEG quantization, and diffusion inversion.
-
What numerical fidelity constraints are used in Equations (2) and (7)? Could the authors provide paired image quality measurements, such as PSNR and LPIPS, together with template and residual magnitude statistics for and the default configuration? A comparison between robustness and fidelity would help clarify the cost of the additional optimization.
6 comments
Response to Reviewer 6eE8 (2/2)
A3. Implementation details (W2, Q2).
For GS and PRC, we replace the hard sign decision on the recovered latent with and minimize
where and is the original watermarked latent. For Tree-Ring and RingID, we minimize the distance between the recovered and target watermark patterns in the Fourier domain. The recovery, fidelity, and alignment losses have weights in code, corresponding to and in Eq. (7).
At each iteration, we uniformly sample four distortions and average their losses. We use the piecewise differentiable JPEG quantization approximation from MBRS [2]. Gradients pass through the VAE encoder and all inversion steps, updating only the per-image residual. Code is available at https://anonymous.4open.science/r/PreFix-640C/.
A4. Robustness–fidelity trade-off (Q4).
Fidelity metrics are computed relative to the original watermarked images before residual addition. Table 3 shows that increasing from 0 to 6 improves robustness (Non-Geo.: 0.919 → 0.968; Geo.: 0.923 → 0.944) with a modest PSNR decrease (38.92 → 37.81 dB), while improving SSIM (0.9561 → 0.9694) and LPIPS (0.0551 → 0.0261). Thus, refinement increases pixel-wise error while improving structural and perceptual similarity, offering a favorable robustness–fidelity trade-off.
Table 3. Robustness–fidelity trade-off (Bit Acc. on SD v2.1).
| Config | PSNR (dB) ↑ | SSIM ↑ | LPIPS ↓ | Residual RMS ↓ | Non-geo. ↑ | Geo. ↑ |
|---|---|---|---|---|---|---|
| GS | - | - | - | - | 0.920 | 0.502 |
| GS-PreFix (K=0) | 38.92 ± 1.58 | 0.9561 ± 0.0163 | 0.0551 ± 0.0316 | 0.0115 ± 0.0021 | 0.919 | 0.923 |
| GS-PreFix (K=6) | 37.81 ± 1.12 | 0.9694 ± 0.0149 | 0.0261 ± 0.0110 | 0.0130 ± 0.0017 | 0.968 | 0.944 |
References
[2] MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression.
Follow-up on Our Response
As the discussion period is coming to an end, we would like to gently follow up and check whether our response has addressed your concerns. If so, we would appreciate it if you could consider updating your score. We are happy to answer any remaining questions.
Response to Reviewer 6eE8 (1/2)
Thank you for your constructive suggestions. To facilitate reproducibility and inspection of implementation details, we provide our code at https://anonymous.4open.science/r/PreFix-640C/. Below, we address your questions.
A1. Comparison with SynTag (W1, Q1)
Both SynTag [1] and PreFix use synchronization for geometric correction. The key distinction is recovery-driven pre-compensation. PreFix uses the watermark recovery loss computed after geometric correction to optimize a per-image residual, whereas SynTag learns synchronization cues independently of the watermark recovery objective. PreFix also optimizes the same residual for watermark recovery under non-geometric distortions. We evaluate SynTag using the code provided by its authors. Tables 1 and 2 show that PreFix achieves higher average robustness under both non-geometric and geometric distortions.
Table 1. Comparison with SynTag on SD v2.1 (TPR/Bit Acc.).
Table 2. Per-distortion results on SD v2.1 (TPR/Bit Acc.).
A2. Contribution of Per-image Optimization (W1, Q1).
Alignment accounts for most of the geometric robustness gain, while per-image optimization primarily improves non-geometric robustness. For GS, K=0 substantially improves geometric bit accuracy (0.502→0.923). Increasing K from 0 to 6 primarily improves bit accuracy under non-geometric distortions (0.919→0.968), with a further gain under geometric distortions (0.923→0.944). A larger K suits forensic tasks that prioritize reliable watermark recovery, while a smaller K is practical for latency-sensitive applications. We will further explore ways to reduce cost, including mixed precision and fewer diffusion inversion steps during optimization.
References
[1] SynTag: Enhancing the Geometric Robustness of Inversion-based Generative Image Watermarking