- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the gap between manipulation observability and fine-grained localization in proactive image protection. Instead of modifying the upstream protection mechanism, the authors propose SPARR, a downstream response-interpretation framework that converts manipulation-sensitive responses into pixel-level tampering masks. The method is evaluated on five conventional tampering benchmarks and four generative-AI editing settings under a fixed upstream protection mechanism. The experiments show substantial improvements over the original Blank Canvas localization outputs on several conventional benchmarks, and the progressive ablation indicates that both PRSR and especially SARD improve F1, IoU, and boundary F1.
Critical strengths
- The paper identifies and clearly formulates a meaningful observability-to-localization gap in proactive image protection.
Existing proactive approaches may successfully expose manipulation-sensitive responses without necessarily producing spatially accurate tampering masks.The paper cleanly separates these two objectives and shows that substantial localization gains can be obtained purely through stronger downstream interpretation while keeping the upstream protection mechanism fixed.
- The progressive design is well motivated and empirically effective.
Critical weaknesses
- The contribution of the SARD acceptance mechanism is not sufficiently isolated from candidate generation and candidate selection.
This raises the question of whether most of the gain is actually due to selecting among Morph/BAC/Wide candidates rather than the proposed accept-or-fallback decision itself.
- The overall pipeline contains many manually specified design choices and thresholds, but their robustness is not sufficiently characterized.
Questions for authors
Q1. Could the authors disentangle the effect of candidate selection from the effect of the SARD acceptance/fallback gate?
Q2. How sensitive is SPARR to the manually specified refinement hyperparameters and thresholds?
In particular, could the authors report sensitivity to the PRSR boundary width / percentile thresholds / area-change threshold and the SARD acceptance thresholds?
Q3. Please clarify the training and transfer protocol of the learned AMSP and SARD selectors across datasets.
2 comments
Part2/2—Response to Reviewer Xzws
W2 / Q2. Sensitivity to PRSR and SARD settings
Thank you for identifying the settings that warranted closer examination. The one-factor-at-a-time PRSR study uses 1,010 images and 12 settings, including the frozen reference. That reference uses a 5-pixel boundary band, lower and upper residual quantiles of 0.20 and 0.80, and a maximum relative mask-area change of 0.12. Each row below varies only the parameter shown.
| PRSR setting | Macro F1 | Boundary F1 |
|---|---|---|
| Frozen reference | 0.76315 | 0.30194 |
| Boundary width 2 px | 0.75548 | 0.29853 |
| Boundary width 3 px | 0.75982 | 0.30058 |
| Boundary width 7 px | 0.76237 | 0.30527 |
| Boundary width 9 px | 0.76093 | 0.31246 |
| Lower quantile 0.10 | 0.76124 | 0.28964 |
| Lower quantile 0.30 | 0.76398 | 0.31768 |
| Upper quantile 0.70 | 0.75771 | 0.28389 |
| Upper quantile 0.90 | 0.75733 | 0.32328 |
| Area-change limit 0.06 | 0.75547 | 0.30869 |
| Area-change limit 0.18 | 0.76548 | 0.29985 |
| Area-change limit 0.24 | 0.76670 | 0.29548 |
An upper quantile of 0.90 lowers region F1 and increases Boundary F1, while relaxing the area-change limit to 0.24 has the opposite effect. We retained the frozen settings throughout the held-out evaluation.
For SARD, the frozen thresholds are 0.002 for predicted utility gain and −0.003 for predicted F1 gain. The utility gain threshold is 0.010 for Wide candidates. Varying only the predicted F1 gain threshold gives the following results.
| Predicted F1 gain threshold | Accepted / 1,010 | Macro F1 |
|---|---|---|
| −0.010 | 1,000 | 0.840183 |
| −0.003 (frozen) | 991 | 0.840147 |
| 0 | 977 | 0.840134 |
| 0.0015 | 968 | 0.840028 |
The archived gate study covers 44 configurations, including the frozen reference, one-factor changes, and joint changes. The one-factor configurations give mean F1 between 0.839683 and 0.840198. The joint changes give mean F1 between 0.839821 and 0.840183. The four settings above show that acceptance counts can change while mean F1 remains close to the frozen result.
Changes in the revised manuscript. Appendix F (p. 18) reports the frozen PRSR setting, the effects of raising the upper quantile to 0.90 and the area-change limit to 0.24, and all four predicted F1 gain thresholds shown above. Appendix B (p. 14) documents the frozen acceptance thresholds, including the stricter utility threshold for Wide. The full 12-setting PRSR grid and the broader gate study are additional detail in this response.
W3 / Q3. Selector training and transfer across datasets
We appreciate the request for a clearer account of the training and transfer protocol. For IMD2020, Dev1000 is used to construct training candidates and fit the downstream predictors. AMSP uses ground-truth-based ranking supervision and validation-based LambdaMART early stopping with patience 40. SARD uses 19,515 development candidate records, 23 features, and a five-fold Ridge ensemble with α = 10 to predict utility and F1 gains.
The 1,010 held-out images are evaluated with frozen selectors and decision thresholds. Prediction uses image and candidate features, and ground truth is used for scoring. The full IMD2020 score combines 1,000 out-of-fold development predictions with the 1,010 held-out predictions. BC protection and SAM remain fixed in these analyses.
Changes in the revised manuscript. Section 4.1 (p. 7) now specifies the training targets, early stopping, Ridge fitting, and frozen inference on IMD2020. Appendix A.1–A.2, Tables 4–5 (p. 13), document the split and use of ground truth. Section 4.2 (p. 8) specifies frozen SPARR predictions for the 1,000-image LaMa evaluation.
The checkpoint and fitting details for each external benchmark remain open. A full account of cross-dataset transfer would identify the checkpoints and any target-dataset fitting or threshold changes for each benchmark.
Part1/2—Response to Reviewer Xzws
Dear Reviewer Xzws,
Thank you for your careful review of Submission 31996 and for recognizing the distinction between manipulation observability and fine-grained localization. We appreciate your suggestions about the SARD gate, parameter sensitivity, and selector training.
W1 / Q1. Separating candidate generation, selection, and gate acceptance
We appreciate the suggestion to separate the effect of ranking from that of the acceptance rule. SARD generates Morph, BAC, and Wide candidates from the PRSR mask, ranks them by predicted sample-specific utility, and applies an acceptance rule that can fall back to PRSR. To isolate selection and acceptance, we held the pool fixed at 18,863 candidate records spanning 24 types on the 1,010 held-out IMD2020 images.
The fixed policy was selected retrospectively using test F1. The oracle uses ground truth to estimate the F1 selection ceiling. Adding the frozen gate changes mean F1 from 0.840198 to 0.840147, and the gate accepts refinements on 991 of 1,010 images. These results suggest that sample-wise ranking accounts for most of the mean improvement in this experiment. The acceptance rule provides a configurable fallback to PRSR.
Changes in the revised manuscript. Section 4.3 (p. 9) summarizes the ranking and gate results. Appendix F, Table 11 (p. 18), presents the comparisons while holding the candidate pool fixed, including the rounded gate-off and gate-on F1 values of 0.8402 and 0.8401.