- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies how to attack 3DGS watermarks using a public surrogate decoder without access to the owner's decoder, message, or verification queries. The authors argue that surrogate gradients do not directly determine an effective attack target and propose AACT. It flips exactly half of the surrogate message bits and selects the subset using a balanced D-optimal criterion based on the strength of gradients with respect to Gaussian appearance parameters and the complementarity of their carriers. The attack updates only bounded SH appearance parameters while preserving geometry and the Gaussian set. SNSS terminates optimization based on the convergence trajectory of the surrogate objective.
Critical strengths
-
The method achieves a practically useful trade-off among attack effectiveness, rendering quality, and computational cost under a strict setting with no owner-side queries.
-
The attack uses publicly available gradients without modifying geometry, making it a useful tool for watermark security evaluation.
-
The supplementary experiments in the appendices substantively strengthen the conclusions rather than merely repeating the main results.
Critical weaknesses
-
The “alignment” metric and controlled experiment do not fully support the proposed mechanistic explanation of the relationship between models. Section 4.1 measures alignment by bitwise agreement between decoder outputs, and Section 4.2 reduces it from 100% to 50% by applying a fixed sign mapping to the surrogate logits. However, this is a relabeling of the output code and does not necessarily reduce the functional or gradient relationship between the decoders in image space. In particular, for BI, if z′ = qz with q ∈ {−1, +1}, the initial pseudo-message flips accordingly, while the signed gradient toward the opposite decision remains unchanged. Its approximate invariance in the controlled experiment therefore has a direct algebraic explanation. The experiment demonstrates stability to code polarity changes, but cannot by itself establish that target ambiguity is resolved for genuinely independent decoders.
-
The additional contribution of the full target-selection procedure over simpler targets requires clearer statistical and computational evidence. In Table 3, the full method does improve target-boundary crossing success and iteration counts, but the paper does not report per-scene paired differences for the main metrics, uncertainty across repeated runs, or the separate overhead of computing per-bit gradients and constructing the carrier kernel. Across different message lengths, AACT does not consistently outperform BI in ΔBAR and IDS, although it performs better in verification pass rates and rendering quality. A better-supported conclusion is therefore that it offers a stable and practical compromise, rather than a universally stronger target construction. The value of the full D-optimal selection should be assessed under equal total runtime or equal image-distortion budgets.
Questions for authors
- Could the authors distinguish output-code agreement from attack-gradient transferability? Please explain why changing only output polarity supports the current interpretation of surrogate–owner alignment, and clarify whether the owner and public surrogate decoders for GM/3D-GSW use the same checkpoint or share training provenance.
- Please provide per-scene paired results and uncertainty for Full versus Random and Strength, and clarify whether the reported total runtime includes all carrier-gradient computations and D-optimal selection. Does the advantage persist under equal total runtime or equal distortion?
- The inversion-aware verification in Appendix C is valuable. Could GMEA also be evaluated under the same protocol, with the number of random test messages reported? This would help determine whether the IDS advantage in the main text translates into consistently stronger disruption of owner verification.
4 comments
Response to Reviewer NV7r W2/Q2 (1/2): What Full Bit Selection Adds
Response to Reviewer NV7r W2/Q2 (1/2): What Full Bit Selection Adds
Thank you for this suggestion. Full selection lowers the inversion-aware pass rate on GS48 to a three-seed mean of 5.52%, compared with 8.68% for Random and 8.16% for Strength. We added per-scene paired comparisons (Appendix H.1, Table 18) and three-seed mean ± population SD (Table 19). All three strategies share the same half-Hamming geometry, appearance optimization, and SNSS, and differ only in which bits they select.
Overall results. The table summarizes GS48 over 15 Blender/LLFF scenes with seed 0, where the strategies differ more than on the near-saturated GM48 setting.
| Selection | ΔBAR ↓ | IDS ↑ | P₂ (%) ↓ | PSNR (dB) ↑ |
|---|---|---|---|---|
| Random | 12.35 | 75.22 | 8.75 | 29.01 |
| Strength | 10.48 | 76.83 | 8.02 | 28.54 |
| Full | 9.31 | 79.90 | 5.73 | 28.60 |
Full lowers by 3.02 percentage points relative to Random and 2.29 points relative to Strength, with PSNR slightly above Strength and below Random. Combining carrier strength and complementarity therefore improves actual owner-verification disruption, beyond reaching the surrogate target.
Per-scene comparison. The table counts the scenes where Full performs better, ties, or performs worse than each alternative.
| Comparison | Metric | Full better | Tie | Full worse |
|---|---|---|---|---|
| Full vs. Random | IDS ↑ | 12 | 0 | 3 |
| Full vs. Random | P₂ ↓ | 4 | 10 | 1 |
| Full vs. Strength | IDS ↑ | 13 | 0 | 2 |
| Full vs. Strength | P₂ ↓ | 5 | 9 | 1 |
These paired results indicate broadly consistent IDS improvements across scenes. For inversion-aware verification, many scenes already achieve zero passes, and among the non-tied scenes, Full generally performs better. These findings support the contribution of carrier-aware selection while acknowledging metric saturation.
Repeated runs. Table 19 reports three-seed mean ± population SD. On GS48, is for Random, for Strength, and for Full.
Revisions. The per-scene results, three-seed variability, and inversion-aware of the selection strategies are already reported in Appendix H.1 (Tables 18–19), and Sec. 4.3 now points to Appendix H. We will also report the mean population standard deviation of BAR, IDS, and PSNR in Table 1, and replace the target-crossing statistics in Table 3(b) with . This provides a more direct assessment of whether carrier-aware selection improves actual owner-side disruption, beyond surrogate optimization behavior.
Response to Reviewer NV7r W2/Q2 (2/2): Computational Cost and Equal-Time Results
Response to Reviewer NV7r W2/Q2 (2/2): Computational Cost and Equal-Time Results
Thank you for raising the cost question. The reported totals include all per-bit gradient, kernel, and selection costs, and Full retains an advantage under equal runtime once sufficient optimization time is available. We added a stage-wise runtime breakdown (Appendix H.2, Tables 20–21) and equal-runtime comparisons (Appendix H.3, Table 22).
Where the cost comes from. The table reports average wall-clock seconds over 15 Blender/LLFF scenes with seed 0 and a fixed 80-step schedule. The total includes preparation, optimization, and output saving.
| Owner | Selection | Per-bit Grad. | Kernel | Selection | Total |
|---|---|---|---|---|---|
| GM48 | Random | 0 | 0 | 0.030 | 48.40 |
| GM48 | Strength | 4.251 | 0 | 0.031 | 52.77 |
| GM48 | Full | 4.750 | 2.929 | 0.043 | 56.88 |
| GS48 | Random | 0 | 0 | 0.031 | 35.55 |
| GS48 | Strength | 3.519 | 0 | 0.037 | 39.07 |
| GS48 | Full | 3.823 | 2.370 | 0.046 | 42.11 |
Full adds 8.48/6.56 s over Random and 4.11/3.04 s over Strength on GM48/GS48. Most of this comes from per-bit gradients and the carrier kernel, while greedy D-optimal selection takes less than 0.05 s.
Results under the same time budget. We compare all three strategies at total budgets of 11, 22, 32, and 43 s (Appendix H.3, Table 22). We highlight GS48 at 32 s, where optimization has not yet reached its final effectiveness.
| Selection | IDS ↑ | P₂ (%) ↓ | PSNR (dB) ↑ |
|---|---|---|---|
| Random | 74.797 | 10.521 | 29.298 |
| Strength | 75.697 | 9.896 | 28.807 |
| Full | 77.702 | 8.021 | 28.960 |
At 32 s, Full lowers by 2.500 and 1.875 percentage points relative to Random and Strength and raises IDS by 2.905 and 2.005 points, with comparable PSNR. It also exceeds Strength in PSNR by 0.153 dB. These gains already include the full target-construction overhead. Random benefits from its lower preparation cost under very short budgets (11–22 s), and at 43 s the results coincide with the unconstrained comparison.
Comparison at similar image quality. Full at 32 s and Random at 43 s reach nearly identical PSNR (28.960 vs. 29.013 dB), while Full yields a lower (8.021% vs. 8.750%). At 43 s, Full also improves both PSNR and over Strength (28.597 vs. 28.537 dB, and 5.729% vs. 8.021%).
Different owner message lengths. We agree that BI achieves slightly better BAR and IDS in several mismatched-length settings in Table 12 of the revised Appendix (Table 10 of the original submission). Across all three settings, AACT achieves equal or lower than both CC and BI, and higher PSNR than BI. This supports AACT's favorable balance between disruption and image quality rather than superiority on every individual metric.
Summary. Full carrier-aware selection provides additional owner-verification disruption at a measurable computational cost, and the equal-runtime results show that this benefit persists after accounting for gradient probing and kernel construction.
Response to Reviewer NV7r Q3: GMEA Under Inversion-Aware Verification
Response to Reviewer NV7r Q3: GMEA Under Inversion-Aware Verification
Thank you for this suggestion. Under the same protocol, AACT achieves lower than GMEA on GM48, while GMEA achieves lower on GS48 at a substantially higher rendering cost. We added GMEA to Appendix Tables 7 and 8 for single-view and multi-view verification, and added per-scene comparisons between GMEA and AACT in Appendix C.3, Tables 9–10.
Single-view verification. The table uses 64 held-out novel views per scene.
| Owner | Attack | P₁ (%) ↓ | P₂ (%) ↓ |
|---|---|---|---|
| GM48 | GMEA | 20.42 | 20.42 |
| GM48 | AACT | 0.00 | 0.00 |
| GS48 | GMEA | 0.10 | 0.10 |
| GS48 | AACT | 5.52 | 5.52 |
Message protocol. GM48 uses one fixed 48-bit owner message across all 15 scenes, while GS48 uses 15 messages randomly sampled from GuardSplat's message set, one per scene. The three seeds share the same messages, and all attacks use the same owner messages and evaluation views. GMEA follows the same three-seed protocol (seeds 0, 1, and 2) as AACT. Table 7 reports the three-seed average, while Tables 9–10 report seed 0.
Interpretation. Although GMEA achieves stronger owner-verification disruption on GS48 ( = 0.10% versus 5.52%), it incurs substantially greater rendering distortion and computational cost. Accordingly, AACT's main advantage is its more favorable balance among attack effectiveness, rendering fidelity, and efficiency, rather than uniformly superior watermark removal.
Response to Reviewer NV7r W1/Q1: Output Agreement and Gradient Transfer
Response to Reviewer NV7r W1/Q1: Output Agreement and Gradient Transfer
Thank you for this careful observation. GaussianMarker and 3D-GSW share the same publicly released HiDDeN weights with our original surrogate, so their 100% agreement reflects a matched-decoder setting. We agree that output agreement and gradient transfer are distinct, and that the polarity experiment alone does not establish transfer between independently trained decoders. We added independent-decoder evaluations, post-hoc gradient diagnostics, and checkpoint provenance in Appendix F.1–F.3 (Tables 13–15).
Why BI is unchanged under polarity relabeling. We agree with your algebraic explanation. For BI, flipping a logit sign also flips its target label, and BCE(−z,1−y)=BCE(z,y), so the loss and its gradient are unchanged. Accordingly, Fig. 4 should not be read as evidence of general cross-decoder transfer. We have revised Sec. 4.2 to describe it as a controlled code-polarity study, while the independent-decoder experiments in Appendix F provide separate evidence under actual decoder differences.
Tests with independent decoders. We evaluate five independently pretrained public surrogates: two Stable Signature (Fernandez et al., ICCV, 2023) HiDDeN48 extractors, TrustMark100 (Bui et al., ICCV, 2025), CIN30 (Ma et al., ACM MM, 2022), and MBRS30 (Jia et al., ACM MM, 2021). Each watermarked asset and owner decoder stays fixed, and CIN30 and MBRS30 use up to 240 optimization steps with SNSS monitoring (Appendix F.1). Over 15 scenes and three seeds, AACT reaches low inversion-aware pass rates on GS48 with all five surrogates (P2=0.42–2.47%). On GM48, the independent HiDDeN variants transfer much better (P2=3.19% and 16.18%) than TrustMark, CIN, and MBRS (P2=93.16–94.34%).
Checking whether gradients transfer. Output agreement measures whether the surrogate and owner return the same bits, not whether optimizing the surrogate objective increases the owner's recovery error. We therefore measure (i) the cosine between the negative surrogate target-loss gradient and the positive owner recovery-loss gradient in the same Gaussian SH appearance-parameter space, and (ii) the owner-loss change after a small step along the surrogate attack direction. Table 15 uses the initial assets, two fixed views per scene, seed 0, and 15 equally weighted scenes.
On GM48, the independent HiDDeN variants show much larger cosine and owner-loss transfer than CIN, TrustMark, and MBRS, consistent with their stronger disruption (IDS 80.61/75.12 versus 14.79–21.53). On GS48, independent HiDDeN, CIN, and TrustMark show owner-loss transfer of about 2.5–2.9×10−3 and strong attacks (IDS 83.06–85.45). Because loss scales differ across owners, we compare these values within each owner. These results indicate that transferable surrogate guidance, rather than output agreement alone, helps explain the owner-dependent outcomes. Owner messages and gradients are used only for this analysis, never during attack optimization.
Beyond the matched setting. With the independent and augmented HiDDeN surrogates, AACT still outperforms GMEA on GaussianMarker in all four metrics: ΔBAR 3.15/12.24 vs. 18.71, IDS 80.61/75.12 vs. 62.60, P2 3.19/16.18% vs. 20.42%, and PSNR 24.91/24.32 vs. 23.33 dB (Tables 7 and 14).
Summary. These analyses separate output agreement from transferable attack guidance. AACT addresses the remaining surrogate target-selection ambiguity using public information, without the owner's bit mapping or gradients. Sec. 4.1 now states the shared decoder weights, and Appendix F.3 details the distinction between output agreement and gradient transfer.