- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies visual-disturbance-induced forensic misattribution (VDFM) in ID document images: non-malicious disturbances may be mistaken for tampering, while suppressing disturbance responses may cause genuine tampering to be missed. The authors introduce DISTURBID-180k, a dataset covering 42 types of visual disturbances, and propose CLEAR-ID. The method uses semantic and spatial priors from an MLLM-based disturbance localizer to form disturbance-oriented and tampering-oriented forensic representations. Low-rank selective modulation then constrains prior-conditioned updates to the tampering features.
Critical strengths
- The problem is practically relevant. The paper addresses both false positives caused by common disturbances such as glare and watermarks, and missed tampering caused by excessive disturbance suppression. These concerns reflect practical needs and warrant further study.
- The dataset and evaluation cover a broad range of conditions. The dataset provides separate annotations for disturbance and tampering regions and includes tampering in text, portrait, and signature fields. Evaluation across different editing systems, unseen disturbances, physical capture disturbances, and an external data domain helps assess performance under varied conditions.
Critical weaknesses
- Comparisons of false positives and false negatives with the closest prior work are missing. The paper does not report disturbance-specific FPR and tampering-specific FNR for closely related methods such as DCLNet. It therefore remains unclear whether CLEAR-ID is better at avoiding false alarms on benign disturbances. See Question 1.
- The contribution of MLLM semantics is not isolated. In Table 2, the full prior and the ground-truth disturbance masks differ in both the information they provide and their representation. The performance difference cannot be attributed specifically to the MLLM’s semantic capabilities.
- The functional roles of the two feature branches are not directly validated. The experiments mainly report final detection performance, without separately evaluating the predictive capabilities of the two branches or their roles in regions where disturbances overlap with tampering. The additional benefit of the provenance-aware design over standard multi-task learning remains unclear.
- Qualitative comparisons are limited. Figure 8 omits important baselines such as DCLNet and the MAER-only configuration, making it difficult to assess the effects of individual modules visually. Representative examples in the main paper, with enlarged crops and explicit annotations of false positives and false negatives, would help show the method’s performance and limitations in challenging regions.
Questions for authors
- The aggregate metrics in Table 1 do not separately report disturbance-related false positives and missed tampering, and F1 does not distinguish their contributions to changes in performance. The TTDMamba module ablations in Table 3 do not replace a direct comparison with closely related methods such as DCLNet. Reporting disturbance-specific FPR and tampering-specific FNR under the same metric definitions and evaluation protocol would provide more direct evidence of CLEAR-ID’s advantage on the central problem.
- In Table 2, the full prior and the ground-truth disturbance masks differ in both information content and representation. This comparison supports the effectiveness of the full prior configuration, but does not attribute the improvement specifically to the MLLM’s semantic understanding. Further controlled comparisons are needed to distinguish the contributions of semantic information and spatial priors while accounting for differences in training data, supervision, and prior representation.
- Different supervision tasks provide reasonable training objectives for the disturbance and tampering branches. However, improved final detection performance alone does not establish the additional value of the provenance-aware representation design. A comparison with a standard multi-task model with comparable parameter counts, supervision tasks, and training settings would help distinguish the benefits of the proposed design from those of additional auxiliary supervision.
- Although the authors allow the two representations to share information, their intended functional roles still require direct validation. Can both and predict visual disturbances, and how well does each support tampering localization? What roles do the two branches play in regions where disturbances and tampering overlap, and where they do not?
- The paper shows reduced false positives relative to the clean-only baseline and some ablation configurations, and LSM reduces the disturbance-related false positives of MAER. However, in Table 3, the full model has a higher UVD FPR than VD-aware TTDMamba (0.35 versus 0.30), but a lower FNR (31.68 versus 38.47). This result reflects a trade-off between false positives and false negatives. How do the authors explain this behavior? At the same tampering recall, does CLEAR-ID still achieve fewer disturbance-related false positives?
5 comments
R3-W2 / R3-Q2: Controlled comparisons with the same spatial prior show the contribution of MLLM semantics
We thank the reviewer for asking us to clarify what information each prior provides. In revised Table 3 (formerly Table 2), we distinguish spatial and semantic priors and include a lightweight alternative.
(1) Controlled comparisons with the same spatial prior isolate the contribution of MLLM semantics.
All methods use the same training data, training settings, and evaluation protocol. Revised Table 3 distinguishes the information provided by each DP creator:
- No prior → SAM ( only): isolates the effect of introducing a spatial VD prior.
- VD-GT Masks ( only): uses the ground-truth VD mask as a spatial prior, serving as a reference upper bound for spatial information alone, not for the full semantic prior.
- Qwen3-VL-4B / CLEAR-ID-4B: both use the same SAM spatial prior, SAM$G_V$. The comparison therefore isolates the difference between the untrained semantic prior in Qwen3-VL-4B and the MLLM semantic prior used in CLEAR-ID-4B.
- SegFormer (+): provides a lightweight alternative under the same downstream setting.
Full revised Table 3 (including both UVD FPR and FNR):
| VD prior / DP creator | CID ↑ | UVD ↑ | UVD FPR ↓ | UVD FNR ↓ |
|---|---|---|---|---|
| No MLLM (No priors) | 69.42 | 66.48 | 0.85 | 33.38 |
| SAM ( only) | 71.28 | 64.77 | 0.67 | 39.38 |
| VD-GT Masks ( only) | 72.09 | 66.10 | 0.77 | 35.52 |
| SegFormer (+) | 66.83 | 63.75 | 1.01 | 34.35 |
| Qwen3-VL-4B (untrained + SAM$G_V$) | 72.31 | 62.22 | 0.64 | 43.24 |
| CLEAR-ID-4B ( + SAM$G_V$) | 75.64 | 74.97 | 0.35 | 31.68 |
Note: The last two rows share the SAM spatial prior (SAM$G_V$), allowing us to isolate the contribution of the MLLM semantic prior . All values are in %; only column-best values are bold.
(2) Lightweight SegFormer cannot replace MLLM semantic priors.
We replace the MLLM-based VD-prior generator with SegFormer, keeping the other CLEAR-ID components and training/evaluation protocols unchanged. SegFormer reaches 63.75 UVD , compared with 74.97 for CLEAR-ID-4B; their UVD FPR/FNR are 1.01/34.35 and 0.35/31.68, respectively. Even when SegFormer fits VD spatial localization well, its semantics do not provide equally useful provenance information.
(3) MLLM zero-shot semantics generalize to unseen VDs and can be transferred across forensic backbones.
MLLM semantic priors help distinguish benign, unseen VDs from genuine tampering. The gain magnitude varies across forensic backbones, but all evaluated experts benefit from CLEAR-ID, showing that the framework is not tied to a single expert. The same open-world semantic knowledge can be reused across different backbones, instead of requiring separate lightweight VD detectors for different disturbance types and forensic models. This gives CLEAR-ID value as a backbone-compatible provenance-aware framework, beyond the gain on any one expert.
5. R3-W3 / R3-Q3 / R3-Q4: Gains mainly come from the design and MLLM semantics, not explicit VD supervision; branch probes explain provenance awareness and modulation
To examine the contribution of auxiliary supervision, the roles of the two branches, and their behavior in overlapping regions, we added a standard Multi-Task baseline and probes on , , and .
(1) The gains mainly come from our method and MLLM semantics, rather than explicit VD-task supervision.
Starting from the same TTDMamba backbone, we add a VD-specific prediction head and jointly train the model with VD and tampering supervision. Revised Table 2 (formerly Table 3) reports the comparison:
| Configuration | SFD F1p ↑ | UVD F1p ↑ | UVD FPR ↓ | UVD FNR ↓ |
|---|---|---|---|---|
| TTDMamba (Clean-only) | 57.83 | 55.75 | 0.98 | 46.31 |
| TTDMamba (Oracle-GT) | 53.43 | 54.52 | 0.00 | 53.36 |
| TTDMamba (Multi-Task) | 65.88 | 64.84 | 0.75 | 37.72 |
| TTDMamba (VD-aware) | 68.34 | 71.00 | 0.30 | 38.47 |
| MAER only | 72.89 | 73.68 | 0.43 | 31.72 |
| MAER + LSM (CLEAR-ID) | 74.37 | 74.97 | 0.35 | 31.68 |
Note: Values are from the revised manuscript. Only the best value in each column is bold; ↑ higher is better, ↓ lower is better. Performance values are in % unless stated otherwise.
The results show that explicit VD-task supervision does help: Multi-Task increases UVD from 55.75 (clean-only) to 64.84. However, it remains below 71.00 for VD-aware TTDMamba, and clearly below 73.68 for MAER-only and 74.97 for full CLEAR-ID. Therefore, simply adding a supervised VD task does not account for our gains. The main contributions come from MAER's provenance-aware representation guided by MLLM semantics and LSM's selective modulation of tampering features.
(2) Relative metrics show that is more VD-oriented, while is relatively more tampering-oriented.
We evaluate both MAER branches using VD and tampering probes, and introduce two relative metrics against the original expert representation : for VD and for tampering as shown in Table 25 .
| Representation | VD task F1p ↑ | Tampering task F1p ↑ | VD task | Tampering task |
|---|---|---|---|---|
| 34.38 | 62.26 | 0.00 | 0.00 | |
| 64.54 | 61.09 | +30.16 | -1.17 | |
| 63.86 | 61.58 | +29.48 | -0.68 | |
| 40.26 | 63.69 | +5.88 | +1.43 |
Note: Values are from the revised manuscript. Only the best value in each column is bold; ↑ higher is better, ↓ lower is better. Performance values are in % unless stated otherwise.
Both branches substantially improve VD perception, but has a larger (+30.16 vs. +29.48), indicating a stronger VD-oriented preference. On tampering, shows a smaller decrease in (-0.68 vs. -1.17), indicating better preservation of tampering evidence. Thus, both branches capture VD provenance information but develop different functional preferences.
This mechanism is also reflected in the FPR/FNR trade-off in Table 2: on UVD, Multi-Task records 0.75/37.72, MAER-only improves this to 0.43/31.72, and full MAER+LSM further reaches 0.35/31.68. In other words, MAER primarily perceives and distinguishes the provenance of VD through semantic information while preserving important anomalous responses; LSM then exploits tampering-oriented factors in the subspace to achieve a finer balance between disturbance-induced false alarms and missed genuine tampering. The probe results and the FPR/FNR ablation consistently support this interpretation.
(3) What happens where VD overlaps tampering?
During data construction we tried to avoid large overlaps, but we also analyzed the overlapping case. Unlike models that suppress all anomalous responses, MAER's tends to preserve overlapping regions containing real tampering. This may create some additional false alarms around the boundary, but it substantially reduces missed tampering. LSM then uses selective modulation in a low-rank space to reduce these false alarms and excessive suppression, achieving a better FPR–FNR balance. The third row of Figure 4 illustrates this behavior.
Finally, we sincerely hope that:
- Reconsideration: We are encouraged that another reviewer has recommended acceptance, recognizing the contributions of our work and the effectiveness of our rebuttal. If our responses have adequately addressed your concerns, we would greatly appreciate it if you could reconsider and, if appropriate, increase your evaluation score.
- Further clarification: If any concerns remain, please do not hesitate to let us know. We would be more than happy to provide further clarification or make additional revisions to address them.
Thank you once again for your time, recognition, and valuable guidance!
We appreciate the reviewer's recognition of the practical importance of VDFM and the contributions of DISTURBID-180k and our evaluation across diverse conditions. Our work highlights the tension between false alarms caused by benign disturbances and missed genuine tampering, and offers both a benchmark and a provenance-aware solution. We believe these contributions are important for reliable real-world ID document forensics. For a more coherent discussion, we first present qualitative evidence, then discuss the FPR/FNR trade-off and direct comparisons with related methods, followed by MLLM priors and the two-branch design. We therefore respond in the order W4 → Q5 → W1/Q1 → W2/Q2 → W3/Q3/Q4.
1. R3-W4: Figure 4 shows how provenance awareness and LSM preserve tampering evidence while reducing false alarms
We revised the qualitative comparison so that the differences in how each method handles VD and genuine tampering can be seen directly.
2. R3-Q5: CLEAR-ID achieves the lowest disturbance-related FPR at the same tampering recall
The reviewer correctly notes the fixed-threshold trade-off: VD-aware TTDMamba has 0.30 UVD FPR and 38.47 FNR, while CLEAR-ID has 0.35 FPR and 31.68 FNR. This difference reflects how the two methods handle anomalous responses: suppressing them can reduce certain false alarms, but also increases missed genuine tampering.
To answer the matched-recall comparison directly, we added Figure 5 (UVD FPR–FNR trade-off curves) to the main paper. The curves show that provenance-aware representation produces a better FPR/FNR trade-off than implicit VD-aware suppression, and that LSM improves this balance further, placing CLEAR-ID on the best trade-off frontier. Thus, at the same tampering recall (the same FNR), CLEAR-ID achieves the lowest disturbance-related FPR.
3. R3-W1 / R3-Q1: Direct FPR/FNR comparisons and trade-off curves confirm CLEAR-ID's advantage under VDFM
We agree with the reviewer's suggestion. Aggregate F1 alone does not separate false alarms caused by benign VD from missed genuine tampering. A direct comparison of FPR and FNR with related methods such as DCLNet, using the same metric definitions, is therefore important.
Accordingly, we revised Table 1 to report disturbance-specific FPR, tampering-specific FNR, pixel-level F1p, and image-level F1i consistently across methods, including DCLNet, as requested. The original IoU and AUC results are still fully reported in Appendix C.1.1, Table 17. As Table 1 shows, CLEAR-ID performs better in the VDFM setting: it effectively controls false positives from benign disturbances while reducing missed genuine tampering.
We also added Figure 5, which compares UVD FPR–FNR trade-off curves with representative methods including DCLNet, FFDN, and ASCFormer. CLEAR-ID remains on the leading trade-off frontier even with these additional comparisons, further demonstrating its advantage for VDFM.