- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Compositional Adversarial Training (CAT). It uses a controller to adaptively select and compose image transformations, so as to improve the robustness of watermarking models against complex post-processing attacks. Experiments show that CAT outperforms the random augmentation baseline across multiple watermarking models and datasets, and achieves favorable performance under compositional attack tests.
Critical strengths
- Compared with single perturbations, the research is more aligned with practical scenarios. The paper considers the impacts on watermarks brought by sequentially composed multiple image processing operations, and conducts evaluations on long attack chains that simulate social media reposting and editing.
- CAT selects attack types and their order step by step conditioned on intermediate images. It introduces an adversarial controller during training without modifying the model inference pipeline.
- With the same number of training updates and augmentation budget, CAT generally outperforms the random augmentation baseline. It achieves strong performance under challenging compositional attacks and out-of-distribution evaluations.
Critical weaknesses
- The appendix experiments show that CAT is nearly ineffective against diffusion-based regeneration, with accuracy close to random guesses. It exhibits limited performance against semantic-level watermark removal. If the method is only effective for conventional processing operations, its practical value is constrained. The paper could further discuss how this applicability boundary impacts real-world watermark protection scenarios.
- CAT’s adversarial search space is constrained by a predefined library of attack primitives. The controller can only select and compose attack sequences from the given image transformations, essentially searching for the worst-case compositional perturbations within a known transformation space. Although the paper evaluates several held-out attacks, the results do not establish how well CAT generalizes to a broader range of transformations beyond those considered.
- The paper compares CAT’s performance with random augmentation, Faster AutoAugment, and several alternative adaptive strategies. However, for RoMark, GAT and Adversarial AutoAugment, it mainly reports training overhead without robustness comparisons on the same watermarking model and attack test sets. Therefore, existing experiments support that CAT has lower training cost under the evaluated settings, but cannot directly confirm whether its robustness surpasses these methods.
Questions for authors
- Could the author further analyze and explain the main reasons why CAT performs poorly against semantic watermark-destruction attacks such as diffusion-based regeneration? How does this limitation affect the method’s practical scope?
- How well does CAT generalize to transformations that are not included in the predefined attack primitive library?
- Under the same evaluation settings, how does CAT perform in terms of robustness compared with RoMark, GAT and Adversarial AutoAugment?
2 comments
Response to Reviewer U74N (2/2)
W3 & Q3: Robustness comparison with RoMark, GAT, and AAA
Prior adversarial methods attack with the wrong kind of distortion or with too much strength, and on the same watermarking model and attack test sets, CAT outperforms RoMark, GAT, AAA, and DADW under an equal compute budget. We fine-tune the same PixelSeal checkpoint, trained for 100 epochs without attacks, with each method for 24 hours on 4 A4000 GPUs. We keep the published hyperparameters of each method: component-wise PGD with T=7 and an ℓ∞ budget of 4/255 for GAT, a 6-point severity grid for RoMark, M=8 policies for AAA, and, for Distortion Agnostic Deep Watermarking (DADW), a two-layer convolutional attack network with 5 gradient steps per watermarking step. We measure a training step at 1.33 s for CAT, 3.75 s for DADW, 4.53 s for AAA, 9.57 s for RoMark, and 16.15 s for GAT, so slower methods complete fewer epochs. We evaluate all models with the attack suite of the main tables and report bit accuracy (%) averaged over SA-1B, CLIC-train, CLIC-test, DIV2K, and MetFaces:
| Method | Depth | Epochs | Identity | Value | Compression | Geometric | Combined |
|---|---|---|---|---|---|---|---|
| GAT | – | 22 | 49.9 | 49.9 | 49.9 | 49.9 | 49.9 |
| RoMark | 1 | 36 | 55.5 | 54.7 | 53.4 | 51.1 | 54.7 |
| DADW | – | 97 | 94.7 | 93.7 | 80.1 | 60.7 | 94.1 |
| AAA | 1 | 57 | 94.8 | 93.9 | 92.4 | 86.0 | 93.5 |
| CAT | 1 | 210 | 100.0 | 99.5 | 99.0 | 94.5 | 98.6 |
| AAA | 2 | 58 | 91.1 | 90.3 | 90.3 | 88.0 | 89.5 |
| CAT | 2 | 183 | 100.0 | 99.5 | 99.5 | 97.2 | 98.7 |
We find that each prior method fails for a reason that follows from its design:
- RoMark and GAT optimize the worst-case strength of fixed transformations for each image. In the first epoch, this pushes the decoding loss above chance level, the decoder converges to an uninformative output, and accuracy stays at chance. When we remove GAT's ℓ∞ component, it still collapses (50.0%), and RoMark's own Algorithm 1 avoids collapse but does not improve on the starting checkpoint (82.6% vs. 83.3% without attacks).
- AAA samples policies that ignore the image and trains on 8 augmented copies of every batch, so it completes only 57 epochs. With CAT, we improve on it by +6.5 pp at depth 1 and +9.2 pp at depth 2, with the largest gains on geometric attacks (+8.5 pp and +9.2 pp), at matched image quality.
- DADW learns local pixel-level perturbations, which cannot express geometric transformations, and reaches only 60.7% under geometric attacks, against 94.5% for CAT.
CAT avoids all three failure modes. We compose real-world transformations, including geometric ones, chosen with their order by a controller conditioned on the image and the intermediate attacked state. We sample strengths from the training distribution, so every training example remains learnable while the adaptive compositions supply the difficulty. CAT is also the cheapest method per step. We will add these results and the per-step costs to the paper.
Response to Reviewer U74N (1/2)
(1/2) We thank the reviewer for recognizing the practical relevance of composed processing operations, effectiveness against long and realistic attack chains, and CAT's strong performance under compositional and out-of-distribution attacks. In what follows, we address all of the reviewer's concerns.
Diffusion-based regeneration removes every imperceptible post-hoc watermark, which prior work proves theoretically, so the chance-level accuracy reflects a limit of any posthoc watermark rather than of CAT. Zhao et al. (NeurIPS 2024) prove that regeneration attacks, which add Gaussian noise to the watermarked image and reconstruct it with a generative model, remove any watermark whose perturbation is small in ℓ2 norm. After the noise is added, the image is nearly indistinguishable in distribution from a noised unwatermarked image, so no decoder can recover the message, however it was trained. Saberi et al. (ICLR 2024) prove a fundamental trade-off between evasion and spoofing errors for watermarks that introduce subtle perturbations, and show that diffusion purification removes such watermarks in practice. Our DiffPure attack follows their setup. Consistent with these results, we find that all six models in Appendix F, trained with random augmentation or with CAT, decode at 50.0% to 51.6% bit accuracy under DiffPure. No training procedure can restore information that the attack destroys, and a watermark strong enough to survive the injected noise would no longer be imperceptible.
CAT does improve robustness to generative attacks that preserve part of the signal. Averaged over the three models, we improve bit accuracy over random augmentation by +4.4 pp under VAE regeneration, +2.9 pp under learned neural compression, and +3.0 pp under semantic region inpainting.
The applicability boundary is therefore the boundary of post-hoc imperceptible watermarking, and CAT targets the threat that falls inside it. Watermarks applied after generation, as in VideoSeal and PixelSeal, must survive the processing that content undergoes when it is distributed: recompression, resizing, cropping, color edits, transcoding, and repeated reposting. These operations are the most common cause of watermark loss, require no attacker, and are what we train CAT against. Deliberate regeneration with a diffusion model requires a different kind of watermark, such as semantic watermarks embedded during generation (e.g., Tree-Ring, Wen et al., NeurIPS 2023), which need control of the generator and cannot mark existing content. We will add this discussion and both citations to the paper.
CAT's gains carry over to transformations outside its library. Every method we compare with draws from a fixed library, and CAT changes how compositions are chosen, not which primitives exist. To answer Q2 directly, we evaluate PixelSeal (depth 1) on SA-1B images against 10 families outside the training library, each at several fixed strengths. We report bit accuracy averaged over strengths, with the LPIPS to the watermarked image:
CAT is ahead on all ten families, by +6.2 pp on average. We further compose these families with each other and with every training family one step beyond its training range (e.g., JPEG quality 30, crop 0.45, rotation 15°), and apply all 342 ordered pairs of two different transformations:
CAT is ahead on 310 of the 342 compositions, by +5.8 pp on average. Against a model-aware attacker that selects, per image, the most damaging transformation or composition of two from a pool including unseen families and training families far beyond their ranges, CAT stays ahead at every LPIPS budget, by +5.9 pp at LPIPS ≤ 0.1 and +3.0 pp at LPIPS ≤ 0.3. The realistic attacks of Appendix F are also outside the library, and there CAT gains +2.9 pp and +20.4 bits under neural compression and +11.1 pp and +41.1 bits under repeated video transcoding. We will add these results to the paper.