- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper embeds a CLIP-derived feature of the prompt in each generated image, so that a verifier holding a bank of N candidate prompts can retrieve the right one. On a frozen Stable Diffusion 1.5, a trainable selector computes the feature, an injector writes it into the initial latent, and a ResNet-18 decoder reads it back. The paper claims four contributions. (1) It backpropagates through the frozen sampler with gradient checkpointing, unlike a detached rollout, which cuts the gradient. (2) It removes an inherited clipping step on the initial latent and uses the injection strength to trade retrieval against fidelity. (3) It states a randomized-smoothing certificate for retrieval and the finite-sample ceiling on its radius. (4) It adds control experiments. The tests use held-out banks of 16 to 512 prompts, three seeds, the training distortions and a projected gradient descent (PGD) attacker.
Critical strengths
The paper reports its own failures and controlled experiments for the obvious limitation.
Critical weaknesses
-
In a mature field of Watermarking Diffusion models, the paper compares with no existing watermark and omits the standard attacks.
-
No existing watermark appears in any table. The stated use case is telling which commission produced an image without "storing a key per generation" (l. 40–42). RingID or Gaussian Shading, keyed by a hash of the prompt, already serves it, since the verifier holds the prompts anyway. RingID reports 0.96 identification accuracy among 128 keys on Stable Diffusion 1.5, against 0.357 here (Table 10).
-
The distortion tests use only the training distortions, at training strengths (App. E). There is no regeneration attack, although Sec. 2 cites such attacks (Zhao et al., 2024). Nor is there crop, rotation or colour correction, although the watermark is "a strong tint" (l. 305).
-
The only adversarial test is weak: 5-step PGD over the five distortion parameters (App. F). It even raises the adversarially fine-tuned model's Top-1 from 0.315 to 0.359 (Table 8). There is no pixel-space attack, no forgery test (e.g. Müller et al., CVPR 2025) and no threat model. Yet the watermark is a keyless function of the prompt, and the checkpoints are released.
-
-
Contributions 1 and 2 are published or fix the authors' pipeline. Backpropagating through a frozen sampler with per-step gradient checkpointing is DRaFT (Clark et al., ICLR 2024), and OptMark (Xing et al., AAAI 2026) does it for initial-noise watermarks. Neither is cited. A detached rollout gives the injector zero gradient by construction (Sec. 3.2), so the chance-level column of Table 1 only checks the implementation. The clipping step is "the configuration we inherited" (l. 186). The task is close to TokenTrace (cited) and SEAL (Arabi et al., ICCV 2025, not cited), which also ties the initial noise to the content.
-
The formal results are borrowed, and the method itself has no theory. Theorem 1 restates Theorem 1 of Cohen et al. (2019) for a special case (l. 206–207). The paper claims the ceiling as contribution 3, but Cohen et al. derive and plot it (their Sec. 3.2.2 and Fig. 5). Jiang et al. (ECCV 2024), (not cited), already smooth a watermark decoder, with certificates against removal and forgery. In this work, nothing explains why, or how much, prompt information survives the sampler.
-
The certified radius is too small to matter. A radius of at noise level is a per-pixel root-mean-square change of (l. 356–357). Rounding a RGB image to bits alone changes it by about in norm. Certification is never run on unwatermarked images, where a verifier that cannot tell when to return no answer may certify a wrong prompt.
-
The paper is poorly presented and very hard to read.
Questions for authors
-
On the same banks of 128 and 512 prompts, how does RingID or Gaussian Shading keyed by a hash of the prompt compare? Please also report the method's detection TPR at 1% FPR. Matching the keyed baseline on exact prompts, or beating it on paraphrased ones, would resolve this concern.
-
What is Top-1 at N = 128 under diffusion regeneration (Zhao et al., 2024) and under the imprinting forgery of (Müller et al. 2025)?
-
For what fraction of unwatermarked images does certification return a prompt, and at what radius? A fraction near zero would show the certificate at least does not certify false attributions.
-
Why does the base model's clean Top-1 differ between tables? Table 8 gives and Tables 2–4 give , under the same checkpoint and protocol (Table 13). Without an answer, I cannot tell which runs back the other tables.