- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
XPlainVerse is a large-scale dataset for explainable deepfake detection, containing one million images and 1.53 million image–explanation pairs. The authors combine multiple image-editing models, an edit-consistency filtering pipeline, and technical and simplified explanations. They also introduce EntityScore and EvidenceScore and evaluate detection and explanation generation under generator and perturbation shifts.
Critical strengths
1.Explainable deepfake detection is a worthwhile research direction, and the dataset provides substantial supervision across different scenes, editing models, and explanation styles.
2.Edit-Check addresses a practical problem in synthetic dataset construction: generated images do not always follow the requested edits. The human comparison of retained and discarded images provides some support for the filtering procedure.
3.The paper includes human-written references, a user study, and detailed supplementary experiments. The large gap between in-domain and out-of-domain performance also exposes weaknesses that would be missed by evaluating only familiar generators.
Critical weaknesses
1.Contribution beyond scale is not sufficiently isolated. The pipeline mainly combines existing models for editing, filtering, and annotation, while Table 1 already lists several datasets using model ensembles and quality control. This does not make the dataset unimportant, but the paper needs controlled comparisons showing what Edit-Check and dual-level explanations contribute beyond collecting more data. Appendix C also clarifies that the million images comprise 500K base images and their perturbed counterparts; the headline scale should not be interpreted as one million independent examples.
-
Proposed metrics measure agreement with reference text, not visual grounding. EntityScore and EvidenceScore compare extracted claims between explanations without checking the image. A prediction that repeats an incorrect reference claim can score well, while a valid observation absent from the reference can be penalized. Cross-family judge agreement in Appendix I is useful, but agreement between models does not establish agreement with human judgments of factual correctness. This is a central limitation given the paper’s emphasis on grounded explanations.
-
The annotation prompts risk producing plausible justifications rather than reliable forensic evidence. Annotators and models know that the image is manipulated and can inspect the original image; generated annotations also receive edit instructions and difference descriptions. Asking them to write “as if” they saw only the edited image does not remove this privileged information. Some prompt examples are particularly questionable: wearing a winter coat on a sunny beach is treated as evidence of manipulation, while dirt and scratches are presented as evidence of authenticity. These are neither necessary nor sufficient indicators and could teach semantic stereotypes rather than forensic reasoning.
-
The generator-shift evaluation is strongly affected by training imbalance. Table 9 shows that 354,256 of 360,000 training fake images—approximately 98.4%—come from Gemini-2.0-Flash. The resulting OOD collapse is therefore difficult to separate from an overwhelmingly single-generator training distribution. The broader-generator experiment helps, but explicitly does not balance generators. Perturbation difficulty also increases across splits, introducing another source of shift. Generator-balanced training and separate clean/perturbed results are needed to isolate the causes of failure.
-
Human study supports perceived quality more clearly than factual reliability or practical usefulness. The paper does include 2,000 human-written explanations and 30 evaluators, but the explanation-quality and preference stages cover only about 118–120 images each. Evaluators were recruited from institutional research groups, which limits the conclusions about ordinary users. Preference for generated explanations over human-written ones does not establish that their individual claims are correct, and reported readability does not show that explanations improve detection decisions. A blinded, claim-level audit and an actual user decision task would provide stronger evidence.
Questions for authors
- Can you validate EntityScore and EvidenceScore against blinded human judgments of individual claims, including incorrect reference claims and valid evidence omitted from the reference?
- How often do explanations contain evidence that is apparent only after seeing the original image or edit instruction? What happens when annotations are generated from the edited image alone, with an option to report insufficient visible evidence?
- How much of the OOD performance drop remains under generator-balanced training and identical perturbation conditions? Please report clean and perturbed results separately.
- At a fixed training size and generator distribution, how do label-only training, unfiltered explanations, Edit-Check explanations, and the two explanation styles compare?
- Are each source image, all its edited variants, and their perturbed counterparts confined to a single split? How are duplicate source images across the five source datasets handled?
- Do simplified explanations improve users’ detection accuracy or confidence calibration, rather than only readability and preference?
- Does your overview of current AIGC image detection datasets omit recent explainable benchmarks, such as Veritas's Benchmark and IvyFake? Please re-evaluate the completeness of your benchmark comparison; since recent datasets across different categories exhibit distinct styles, you should highlight the differences among these CoT' AIGC Detection datasets.
[1] Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning [2] Ivy-fake: a unified explainable framework and benchmark for image and video aigc detection
5 comments
Response to Reviewer 1hQh (Part 2/3)
Q3. Generator balance and perturbations
Sec. 5 and Appendix J (Table 24) report our generator balanced training study with Qwen3.5-4B and BusterX++. The fake-image portion of this mixture covered five generators: Gemini-2.0-Flash, LongCat, Hunyuan, ICEdit, and GPT-Image-1. We excluded seven additional generators from fine-tuning and evaluated them as held-out generators: FLUX.1-dev, GPT-Image-1.5, Nano Banana 2, Nano Banana Pro, Qwen-Image-Edit, Seedream 4.5, and Wan 2.6.
To examine the role of perturbations, we evaluated both models separately on clean images and their perturbed counterparts, covering all twelve generators. Within each condition, we calculated fake-image accuracy (recall on fake images) for each generator, then averaged equally across the five training generators and, separately, the seven held-out generators.
| Model | Condition | Seen Fake Acc. | Held-out Fake Acc. | Gap |
|---|---|---|---|---|
| Qwen3.5-4B | Clean | 84.9% | 46.9% | 38.0 pp |
| Qwen3.5-4B | Perturbed | 80.6% | 51.0% | 29.6 pp |
| BusterX++ | Clean | 86.1% | 46.5% | 39.6 pp |
| BusterX++ | Perturbed | 81.6% | 51.1% | 30.5 pp |
Table 4: Clean and perturbed results after five-generator fine-tuning.
When both generator groups are evaluated on clean images, the gap remains 38.0 percentage points for Qwen and 39.6 for BusterX++. On the corresponding perturbed images, the gaps are 29.6 and 30.5 points, respectively. A substantial gap therefore persists under balanced generator training in both conditions. This supports the finding in Sec. 5 that strong performance on training generators does not ensure comparable performance on held-out generators.
Q4. Edit-Check and explanation supervision
In the construction pipeline [Sec. 3.1, Steps 3 and 5], explanations are generated for retained edits; discarded edits do not have explanations. An unfiltered-explanation training condition is therefore not available in the dataset. The human evaluation in Sec. 3.3, Fig. 4(b), and Appendix H (Stage 2) directly compares retained and discarded edits. Retained edits receive a composite edit-fidelity score of 3.77/5, compared with 2.66/5 for discarded edits. These results support Edit-Check's role in selecting higher-quality edits.
To examine the contribution of explanation supervision, we conducted an additional experiment in which we trained BusterX++ using labels alone, while preserving the same hyperparameters and training data. Table 5 compares the new label-only results with the explanation-supervised results on the same ID/OOD evaluation images. Each setting uses its intended prediction format: a class label for label-only models, and an explanation followed by the label for explanation-supervised models.
| Training supervision | ID F1 (%) | OOD F1 (%) |
|---|---|---|
| Label-only | 88.84 | 41.85 |
| Label + complex explanations | 91.89 | 37.14 |
| Label + simple explanations | 92.45 | 37.87 |
Table 5: Fake-class F1 under different supervision settings.
Compared with the explanation-supervised models, label-only training gives a similar result, with 3.05–3.61 percentage points lower ID F1 and 3.98–4.71 points higher OOD F1, thus a substantial ID/OOD gap still persists. Thus, the generalization difficulty reported in Sec. 5 is not solely a consequence of requiring models to generate explanations. It remains even when they are trained to predict labels alone. We will include this comparison and its training details in the paper.
Response to Reviewer 1hQh (Part 3/3)
Q5. Source splits and duplicates
Each clean image and its perturbed counterpart are kept in the same split. For the protocol in Sec. 5 and Appendix C, we chose to define ID/OOD by generator exposure. Different generators can introduce different visual artifacts, and our aim is to test whether detectors generalize beyond the generators represented during fine-tuning. We did not additionally require all edits of a source image to remain in one split. The original image and different edited versions can therefore occur across splits.
For duplicates across the five source datasets, our provenance audit compared SHA-256 file hashes and, where available, hashes of decoded image pixels, to identify exact duplicate source images.
Q6. Simplified explanations and user outcomes
Our primary objective with simplified explanations is to make the evidence behind a detection decision more accessible to non-expert users, rather than to improve their independent deepfake detection accuracy. Accordingly, our human study focuses on users' perceived understanding, memorability, and effort [Sec. 3.3; Appendix H, Stage 6, Tables 17–18]. Across 119 images and 360 evaluations, simplified explanations received 3.99/5 for immediate understanding, 3.97/5 for memorability, and 2.13/5 for effort (lower is better). These results support their perceived accessibility beyond preference alone.
Q7. Veritas and Ivy-Fake
Thank you for highlighting these benchmarks. We will include both in the dataset comparison in Table 1 and the related-work discussion in Sec. 2.
HydraFake, introduced with Veritas [1], focuses on facial forgeries and contains 100K images. Veritas provides 36K reasoning-annotated training examples that organize forensic evidence into stages such as planning and self-reflection. Ivy-Fake [2] covers both images and videos, with explanations describing spatial artifacts and, for videos, temporal inconsistencies. Its paper reports approximately 106K image/video training samples.
Table 6 compares their explanation supervision and evaluation with XPlainVerse's scene-edit filtering and dual explanation styles [Sec. 3.1, Steps 3–5], human evaluation [Sec. 3.3], and perturbation protocol [Appendix F].
| Resource | Explanation / reasoning emphasis | Evaluation or construction emphasis |
|---|---|---|
| Veritas / HydraFake | Pattern-aware reasoning annotations, including planning and self-reflection | Hierarchical generalization across architectures, forgery techniques and domains |
| Ivy-Fake | Explanation annotations and reasoning chains for image/video AIGC detection | Multimodal training data and a manually verified evaluation set |
| XPlainVerse | Technical and simplified explanations for different readers | Instruction-based scene edits, Edit-Check filtering, and clean/perturbed robustness evaluation |
Table 6: Scope and emphasis of recent explainable detection benchmarks.
We will use these distinctions to expand Table 1 and Sec. 2, and explain how XPlainVerse's technical and simplified annotation styles differ from the structured reasoning annotations used by Veritas and Ivy-Fake.
References
[1] Hao Tan et al. Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning. arXiv:2508.21048v2.
[2] Changjiang Jiang et al. Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection. arXiv:2506.00979v6.
Response to Reviewer 1hQh (Part 1/3)
We are sincerely grateful to the reviewer for their careful assessment and constructive feedback. We greatly appreciate the time and effort devoted to reviewing our work.
Q1. Human validation of the metrics
We appreciate this important question. Firstly, our existing human study [Sec. 3.3; Appendix H, Stage 3, Tables 17–18] evaluates the visual grounding and completeness of reference explanations using only the edited image, without the original image, editing instructions, or difference descriptions. Across 118 images and 360 evaluations, the explanations receive 4.05/5 for grounding, 3.82/5 for completeness, and 2.40/5 for unsupported claims (lower is better). These results provide independent human evidence regarding the visual support and coverage of the reference explanations.
To further validate EntityScore and EvidenceScore against human judgments of entity and evidence correspondence, we conducted an additional human study on 100 reference–prediction explanation pairs, with two ratings per pair. Participants saw explanations labelled A/B and counted, for each explanation, the total entities and evidence observations and how many were also present in the other explanation. Using the definitions in Appendix I, we calculated scores from each response and averaged the two human scores for each pair. Table 3 compares the automatic scores with these human-derived scores.
Table 3: Agreement with the mean human-derived score over 100 explanation pairs. Scores lie in [0,1].
Both metrics show high correlations and low absolute errors, indicating that their scores closely reflect human assessments of the shared entities and evidence on these pairs. This supports their intended role as reference-based explanation metrics [Sec. 4; Appendix I]. We will add these details in our paper as well.
Q2. Edited-image-only explanation generation
Firstly, Our human study in Sec. 3.3 and Appendix H evaluates the original explanations using only the edited image, without the original image, editing instruction or difference description. Across 118 images and 360 evaluations, grounding receives 4.05/5 and unsupported claims receive 2.40/5, where lower is better [Stage 3, Tables 17–18]. These ratings support the visible grounding of the evaluated explanations.
To further examine what happens when annotations are generated from the edited image alone, we conducted an additional experiment with Qwen3.5-27B on 500 images, sampled approximately evenly across twelve editing generators. We withheld the original image, editing instruction and difference description used in the annotation pipeline [Sec. 3.1, Step 5], as well as the edited label. The model could either generate an explanation based on visible evidence or report insufficient visible evidence.
Under this setting, the model generated explanations for 289 images (57.8%) and reported insufficient visible evidence for 211 images (42.2%). Thus, relying on the edited image alone left a substantial proportion of the sampled images without an explanation. This motivates providing contextual guidance during annotation. The additional inputs in our pipeline are intended to help the model identify relevant regions, while the explanation prompt requires the final claims to describe evidence visible in the edited image [Appendix K.6]. Our human evaluation then assesses the resulting explanations using only the edited image [Sec. 3.3; Appendix H]. We will include this additional experiment and its prompting conditions in the revised paper.