- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper studies multi-bit watermarks inserted by the denoiser of a text-to-image diffusion model. It argues that a watermark LoRA active at every sampling step, as in AquaLoRA, changes layout and content relative to the watermark-free image from the same prompt and seed. ResMark keeps AquaLoRA's message-conditioned LoRA and pretrained watermark encoder and decoder, and changes three things. It trains the LoRA only on low-noise timesteps (). It switches the LoRA on only for the last of solver steps. Its teacher-relative loss (TRI) makes the LoRA's clean-latent estimate match the frozen model's estimate plus the watermark residual, the encoder's output for the message.
Experiments on Stable Diffusion and PixArt- compare ResMark with Stable Signature, LaWa, StableGuard, MOLM and AquaLoRA. They measure detection, paired fidelity to the watermark-free image (PSNR, SSIM, LPIPS), FID and robustness to 10 distortion and regeneration attacks.
Critical strengths
The paper aims at an important problem of Diffusion Watermarking. The ablation on PixArt separates what each part of the method does.
Critical weaknesses
-
The novelty is limited. Each part comes from earlier work. The LoRA, message mapper and watermark encoder and decoder are AquaLoRA's. TRI (Eq. 2) is the first term of SleeperMark's Eq. 6, as the paper notes. WaDiff (Min et al., ECCV 2024, not cited) already applies a per-user message only below a timestep threshold, in training and sampling, to keep outputs from the same noise consistent. The novelty claim at L125-127 does not hold.
-
The trained LoRA adds little over adding the watermark residual directly to the final latent (App. D.3, PixArt). On clean images this shortcut reaches 96.92% bit accuracy and PSNR 31.89 dB, against 98.39% and 32.69 dB for ResMark (Table 10). ResMark's lead in bit accuracy is 7 to 10 points under SDEdit and Rinse-2 (Table 11). The gain is even worse under attacks.
-
The only analysis does not explain why the method works. It shows that a change at an earlier sampling step passes through more later steps (App. B), which is true by construction. Appendix B shows this does not imply that early changes cause more drift (L770-771). Nothing explains why TRI works or why the watermark survives regeneration.
-
Inversion-based baselines are missing. The paper puts LoRA deactivation and white-box removal out of scope. In the owner-controlled setting that remains, inversion-based methods apply directly. The paper cites Tree-Ring and Gaussian Shading but does not compare with them. Shallow Diffuse (NeurIPS 2025, not cited) reports this paper's paired-fidelity metrics with detection rates under regeneration, rinsing and averaging attacks, so the comparison is feasible but totally not conducted.
-
The comparison is unfair. Many new watermarking methods are missed in the comparison of this work, including: [1-4]. I request the authors compare with these works.
[1] Xiaoxiao Hu, Jiaqi Jin, Sheng Li, Wanli Peng, Xinpeng Zhang, and Zhenxing Qian. Spherical watermark: Encryption-free, lossless watermarking for diffusion models. In The Fourteenth International Conference on Learning Representations, 2026.
[2] Jan Kociszewski, Hubert Jastrzebski, Tymoteusz Stepkowski, Filip Manijak, Krzysztof Rojek, Franziska Boenisch, and Adam Dziedzic. SERUM: Simple, efficient, robust, and unifying marking for diffusion-based image generation. In The Fourteenth International Conference on Learning Representations, 2026.
[3] Samuel Gunn, Xuandong Zhao, and Dawn Song. An undetectable watermark for generative image models. In International Conference on Learning Representations.
[4] Wenda Li, Huijie Zhang, and Qing Qu. Shallow diffuse: Robust and invisible watermarking through low-dim subspaces in diffusion models. In Advances in Neural Information Processing Systems 38, NeurIPS 2025, pp. 170876–170906. Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2025. doi: 10.52202/085713-5147.
-
Each attack is run at one mild setting, such as SDEdit at strength 0.1, and scored only by bit accuracy (Tables 2 and 6). At the paper's false-positive rate of about 1e-6, a 48-bit message needs 41 correct bits for detection. After Rinse-2, ResMark recovers 36.8 bits on average (76.64%). Unless the per-image distribution is strongly bimodal, most Rinse-2 images go undetected. The paper does not run the attacks it cites to motivate denoiser-side insertion (Zhao et al., 2024; Liu et al., 2025; L44).
-
The paper doesn't evaluate the robustness under adversarial [9], new removal [10-11], or forgery attacks [5-8], which are evaluated by many existing works. I request the authors to evaluate with these attacks to show the robustness of the method.
[5] Pei Yang, Hai Ci, Yiren Song, and Mike Zheng Shou. Can simple averaging defeat modern watermarks? volume 37, pp. 56644–56673, 2024a.
[6] Anubhav Jain, Yuya Kobayashi, Naoki Murata, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji, Niv Cohen, Nasir Memon, and Julian Togelius. Forging and removing latent-noise diffusion watermarks using a single image. arXiv preprint arXiv:2504.20111, 2(7), 2025.
[7] Andreas M¨uller, Denis Lukovnikov, Jonas Thietke, Asja Fischer, and Erwin Quiring. Black-box forgery attacks on semantic watermarks for diffusion models. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20937–20946. IEEE, 2025.
[8] Ziping Dong, Chao Shuai, Zhongjie Ba, Peng Cheng, Zhan Qin, Qinglong Wang, and Kui Ren. Wmcopier: forging invisible watermarks on arbitrary images. volume 38, pp. 138035–138065,2026.
[9] Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, et al. Waves: Benchmarking the robustness of image watermarks. In International Conference on Machine Learning, pp. 1456–1492. PMLR, 2024.
[10] Aistov, K., Abud, K., Serzhenko, I., Kovalev, E., Yakushev, A., Akimenkov, A., ... & Antsiferova, A. (2026). Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking. arXiv preprint arXiv:2610.02010.
[11] Kassis, A., & Hengartner, U. (2025, May). Unmarker: A universal attack on defensive image watermarking. In 2025 IEEE Symposium on Security and Privacy (SP) (pp. 2602-2620). IEEE.
Questions for authors
-
What is the TPR at your false-positive rate of about 1e-6 under each attack in Table 2? Please include SDEdit and rinsing at two or three increasing strengths.
-
How does ResMark compare with Gaussian Shading, Tree-Ring and Shallow Diffuse on Stable Diffusion 1.5 under your protocol?
-
How does ResMark stand under the averaging removal and forgery attacks that MOLM, a Table 1 baseline, evaluates? Given Appendix D.3, I expect forgery to succeed. Evidence otherwise would largely address my concern.
-
What does ResMark's schedule do that WaDiff's timestep threshold does not, beyond exactly recovering the base model while the LoRA is off and using a narrower window? A comparison, or an argument for why that matters, would change my novelty assessment.
-
Why are your LaWa PSNR and MOLM bit accuracy lower than in their own papers? LaWa's paper reports PSNR 33.52 dB at 48 bits, against your 29.05 dB. MOLM's paper reports about 98% bit accuracy, against your 89.10%. At 33.52 dB, ResMark would not be the best on PSNR.