- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes CLOVER, a training framework for explainable AI-generated image detection. It pairs a large binary-labeled corpus, which provides broad coverage of forgery sources, with a much smaller scene-diverse evidence corpus. These are used for joint supervised fine-tuning on binary detection, explainable detection, and label-conditioned explanation. Two-stage reinforcement learning then follows, using only authenticity labels. A frozen self-judge verifies each evidence claim against the image, and a separate judge groups overlapping claims so that repeated evidence is rewarded once. The first stage rewards discovering supported evidence, and the second strengthens penalties for uncertain or invalid claims. Across five detection and three explanation benchmarks, with ablations and a blinded expert assessment, the SFT model achieves the best average detection macro-F1 among the compared methods. RL further improves explanation precision and reduces hallucinations with little change in detection.
Critical strengths
- Explanation improvements without reference explanations. The claim-level self-judge and semantic grouping reduce hallucinations and improve precision.
Critical weaknesses
- Generator overlap complicates the attribution of detection gains. CLOVER is trained on 35 generator groups, and Table 7 shows that several evaluation sets share generator families with training. Evaluation on fully held-out generator families, together with representative baselines retrained under matched generator coverage, would help separate methodological gains from the benefits of broader training data.
- The evaluation provides limited evidence of reliability under realistic online conditions. The paper reports no robustness tests against common distribution shifts such as JPEG compression, resizing, and reposting, and its only in-the-wild set contains no real images, so false positives remain untested. Robustness evaluation under these perturbations, together with results on one or two additional in-the-wild benchmarks containing real images (e.g., Chameleon, WildRF, SocialRF, or SynthWildX), would provide stronger evidence of practical reliability.
- The general-purpose MLLM comparisons could be more current. The strongest general-purpose baselines come from the Qwen3-VL and InternVL3.5 families, while more recent open-weight multimodal models such as Qwen3.6-27B are not evaluated. Evaluating such models under the same protocols would clarify whether CLOVER's explanation advantages persist.
Questions for authors
Please address the points raised in the Weaknesses section
2 comments
Response to Reviewer 1vSo (2/2): Real-World Reliability and Updated MLLM Comparisons
W2. Reliability under realistic online conditions.
CLOVER has lower false-positive rates on real in-the-wild images than the compared baselines. Additional experiments quantify corruption effects on both detection and explanation.
(a) The original evaluation includes real social-media images. SoFake-OOD-v3 includes platform-native real images and preserves their original dimensions and compression characteristics. CLOVER-RL achieves 93.70% macro-F1 on this benchmark, whose evaluation content is disjoint from training. Official dataset description.
(b) Independent in-the-wild real images directly test false positives. We evaluate all models on the same 1,000 independent real in-the-wild images, with no training-content overlap and fixed decision rules.
| Method | GPT-Image2-wild fake recall ↑ | In-the-wild real-image FPR ↓ |
|---|---|---|
| Qwen3-VL-8B | 77.40 | 18.20 |
| FakeVLM | 59.13 | 24.60 |
| CLOVER-SFT | 86.73 | 9.50 |
| CLOVER-RL | 85.33 | 9.70 |
Values in %. Recall and FPR are measured on separate fake-image and real-image sets.
Relative to Qwen3-VL-8B, CLOVER-RL increases fake recall by 7.93 points and reduces real-image FPR by 8.50 points, improving both detection and false-positive control.
(c) Corruption effects are quantified across five detection and three explanation benchmarks. All conditions use the original CLOVER-RL checkpoint and fixed inference settings, without adaptation or threshold tuning.
| Condition | Detection avg. macro-F1 ↑ | FC Precision ↑ | FC Hall. Rate ↓ | FC Evi@Img ↑ | FC Notice rate |
|---|---|---|---|---|---|
| Original | 92.35 | 61.46 | 9.29 | 70.43 | 17.89 |
| JPEG Q70 | 91.06 | 60.10 | 9.80 | 68.80 | 19.30 |
| JPEG Q30 | 87.06 | 55.20 | 11.60 | 63.10 | 26.40 |
| Resize 0.5× | 90.04 | 58.40 | 10.20 | 66.90 | 22.20 |
| Gaussian blur (σ=1.5) | 88.30 | 56.70 | 10.90 | 64.80 | 24.30 |
| Screenshot | 89.50 | 57.80 | 10.60 | 65.90 | 23.20 |
Detection is averaged equally across five benchmarks. FC denotes FakeClue-Evidence; Notices and empty explanations remain in its evaluation denominator.
JPEG Q70, resizing, and screenshots reduce average detection macro-F1 by 1.29, 2.31, and 2.85 points, respectively. JPEG Q30 reduces it by 5.29 points, while supported-image coverage decreases by 7.33 points, Notice rate rises by 8.51 points, and hallucination rate rises by 2.31 points. Under severe corruption, the model abstains more often, but additional evidence loss and unreliable claims remain.
Screenshots use a fixed browser, 100% page zoom, DPR=1, and aspect-preserving display at a 512-px long edge, capturing only the image region. TriDF measures retention of the original reference evidence; LOKI uses corrupted full images and corresponding crops extracted after corruption; FC verifies claims against the corrupted images.
W3. More recent general-purpose MLLM baselines.
With Qwen3.6-27B added, CLOVER-RL still leads in detection and every reported explanation metric.
| Method | Detection avg. macro-F1 ↑ | TriDF-A F₀.₅ ↑ | TriDF-B F₀.₅ ↑ | LOKI Overall ↑ | FC Precision ↑ | FC Hall. Rate ↓ | FC Evi@Img ↑ |
|---|---|---|---|---|---|---|---|
| Qwen3.6-27B | 81.41 | 38.41 | 26.82 | 71.26 | 33.60 | 10.96 | 40.47 |
| CLOVER-SFT | 92.44 | 43.47 | 36.15 | 67.69 | 54.84 | 14.55 | 65.48 |
| CLOVER-RL | 92.35 | 48.62 | 41.01 | 73.52 | 61.46 | 9.29 | 70.43 |
FC denotes FakeClue-Evidence.
CLOVER-RL leads by 10.94 points in average detection macro-F1, 27.86 points in FC precision, and 29.96 points in supported-image coverage, while reducing the hallucination rate by 1.67 points. Its explanation advantage spans precision, coverage, and hallucination control.
Response to Reviewer 1vSo (1/2): Generator Generalization and Matched-Coverage Evaluation
W1. Generator overlap and attribution of detection gains.
Unseen-generator tests and matched-coverage retraining both support CLOVER’s detection advantage. Controlled ablations also validate specific training choices.
(a) CLOVER retains its lead on entirely unseen generators. Z-Image, HunyuanImage-3.0, and BAGEL were excluded from task training and model selection. Using the original checkpoint, CLOVER-RL achieves 79.90 average macro-F1, exceeding Qwen3-VL-8B and FakeVLM by 18.70 and 10.00 points, respectively, and leading on every family.
After excluding the Nano Banana and GPT Image families from all training stages and retraining with matched data volume and training budgets, CLOVER-RL still achieves 76.10 macro-F1 on Nano-banana, exceeding FakeVLM by 7.59 points, and 84.00% fake recall on GPT-Image2.
(b) With matched training coverage, CLOVER leads on all five benchmarks. We retrain D³, the strongest binary-only baseline in our evaluation, on the same 100K binary-labeled images, matching generator sources and the real/fake ratio.
Detection macro-F1 (%), averaged equally across five benchmarks.
Broader coverage improves D³ by 7.15 points, but CLOVER-SFT/RL still lead by 3.47/3.38 points. Training coverage contributes to performance; matching it does not eliminate CLOVER’s advantage.
(c) Same-data, same-backbone evidence supports the label-conditioned task. With data, backbone, and total training presentations fixed, Table 14(b) shows gains of 3.44 points in explanation precision and 2.96 points in TriDF-B F₀.₅, while maintaining detection performance. This directly validates the training design.