- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Existing AI-generated image detectors tend to over-rely on global semantics, limiting sensitivity to the critical micro-defects. To address this issue, this paper proposes Micro-Defects expose Macro-Fakes (MDMF), a local distribution-aware detection framework that amplifies micro-scale statistical irregularities into macro-level distributional discrepancies. Furthermore, the authors introduce a learnable Patch Forensic Signature to avoid localized forensic cues being diluted by plain aggregation. Then they use Maximum Mean Discrepancy (MMD) to quantify distributional discrepancies between generated and real images. A theoretical analysis shows that the patch-wise modeling yields provably larger discrepancies. Extensive experiments demonstrate the effectiveness of the proposed method across multiple benchmarks.
Critical strengths
- Well-motivated problem. The authors state that local micro-defects matter in AI-generated image detection task, which is coherent with common sense and widely recognized by related area.
- Theoretical proof. The authors provide a theoretical analysis in sec 2.4 to support their proposed method, which should be beneficial.
- Experiments on generated videos. The authors conduct further experiments on generated videos in Fig.3, which further demonstrate the effectiveness of the proposed method.
- This paper is well-organized and easy to follow.
Critical weaknesses
- Intuition novelty. Although I acknowledge this paper's intuition that local artifacts matter, this has been widely recognized in this area, and I believe there are already enough works proposed based on this intuition. More discussions on the differences with these works are needed. It is truly hard to say 'a new perspective' as the authors stated in the contribution part.
- Technique novelty. Although I acknowledge the effectiveness of the proposed method, it involves many existing techniques, such as DINOv2, MMD, local patch learning. More justifications of the technique novelty are required.
- Theoretical proof. The analysis depends on restrictive assumptions. Will it still work under more general real-world settings? And does the theoretical theorem 2.7 still hold for single image inference? Besides, I think the performance should be highly related to the images chosen as reference set, did the authors conduct further analysis on this?
- More realistic and advanced generators. The proposed method performs well on the chosen benchmarks. However, the tested generators are somewhat old. With the generators still evolving, the generated image may be more realistic and have no recognizable local artifacts. Did the authors test on more recent and stronger generators? This should provide more support for their proposed method's superiority.
Questions for authors
Please see the weakness above. My major concerns focus on the novelty, theoretical analysis, and generalization under stronger generators. Thus, I currently lean towards a negative rating.
3 comments
[2/3] Rebuttal by Authors
W3a: Restrictive assumptions and more general settings
R2: Thanks for this insightful question. The Gaussian surrogate in PFS space provides the closed form of Proposition 2.6, and Appendix B.4 already notes that the Gaussian kernel gives a positive MMD whenever the distributions of the PFS fields differ. The random sign in Assumption 2.3 describes defects without a preferred direction, which is the regime in which Proposition 2.5 shows that pooling attenuates the shift. The positivity of the population MMD and the separation in Corollary B.4 hold for any defect distribution that shifts the mean PFS, as shown below.
Theoretically, ① let a defective patch have embedding , where follows any distribution and may depend on , the defect indicator is independent of , and has the same distribution for real and generated images. Then the PFS mean shift has the exact form . Assumption 2.3 is the special case of this defect model with .
② A nonzero shifts the mean of the PFS field, so real and generated images induce different field distributions. Since the Gaussian kernel of Eq. 4 is characteristic on the field space, the population MMD is positive without the Gaussian surrogate.
③ Lemma B.3 requires only i.i.d. samples and a bounded kernel that is fixed independently of them, so Corollary B.4, whose condition involves only the population MMD, separates sets of real and generated test images whenever this MMD exceeds twice the finite-sample term.
Empirically, computing the PFS of every patch before pooling improves over the global-pooling baseline on the same frozen backbone under the same BCE objective (93.22 vs. 90.14 AUROC, Table 2), in line with Proposition 2.5. The shift in ① is also measurable, since is the difference between the mean PFS of generated and real patches. On the ImageNet test set, this shift is nonzero for all nine generators under each of the five trained heads with W = 32 in Table 10, and none of the 45 image-level bootstrap 95% confidence intervals contains zero. We have added this generalization to Appendix B and the measured shifts to Appendix E.4.
W3b: Theorem 2.7 and single-image inference
R3: Thanks for this important question. We would like to first clarify that the single-image score of Eq. 6 is analyzed by Proposition B.5 in Appendix B.5, while Theorem 2.7 is stated for sets of test images and does not directly apply to a single image. Theorem 2.7 uses the unbiased MMD estimator, which requires at least two test images, whereas Eq. 6 uses the biased estimator with one test image. For a real image and a generated image with a positive population similarity margin , Proposition B.5 shows that a bank of real references assigns the higher score to with probability at least . The ordering of two test images is therefore determined by their margin and becomes insensitive to the sampled references as grows. Consistently, replacing the reference bank with other ImageNet images changes the average AUROC by at most 0.01 (see R4). We have revised the case labels and the interpretation of Theorem 2.7 in Section 2.4 so that they refer to sets of test images and point to Proposition B.5 for the single-image score.
[3/3] Rebuttal by Authors
W3c: Dependence on the reference set
R4: Thanks for raising this point. We would like to first claim that we have varied the reference size from 1k to 10k (Table 12 in Appendix E.7) and replaced the ImageNet references with LSUN-Bedroom images, with little change in either case. To further examine the composition of the reference set, we keep the five trained heads with W = 32 in Table 10 fixed and replace only the reference bank, which all five heads share in the paper. We draw ten new disjoint 3k banks from ImageNet training images, restrict the bank to 30 or 300 classes, compress the references with JPEG, and use 1,750 MSR-VTT video frames as a cross-domain bank. Cells report average AUROC and AP over the five heads (mean±std in the first two rows and the last row).
| Reference set | AUROC | AP |
|---|---|---|
| Paper bank (3k ImageNet images) | 94.97±0.45 | 96.65±0.27 |
| Ten new 3k ImageNet banks | 94.97±0.44 | 96.65±0.27 |
| 30 / 300 classes | 94.98 / 94.97 | 96.65 / 96.65 |
| JPEG references (q = 75) | 94.97 | 96.64 |
| MSR-VTT frames (cross-domain) | 93.93±1.76 | 96.08±0.95 |
Within the ImageNet domain, the average AUROC stays within 0.01 of the paper bank, and for a fixed head the standard deviation across the eleven random banks is 0.009 on average. This stability agrees with Proposition B.5, since the ordering of two test images is set by their margin once the bank is large enough. The 30-class bank also performs like the 300-class bank, in line with the reduced category decodability of the learned patch representation (Table 8). A bank of video frames from another domain lowers the average AUROC by about 1.0, so real references from the target domain are preferable under a large domain change. On ImageNet, a bank of 1k such references already performs like one of 10k (Table 12). We have added this analysis to Appendix E.7 and updated the discussion of the reference set in Appendix E.7 and Appendix G with these results.
W4 (Q): More recent and stronger generators
R5: Thanks for this question. Following your suggestion, we evaluated MDMF on X-AIGD [7], a recent benchmark with 13 text-to-image generators including FLUX.1-dev, SD 3.5 Large and Infinity. Its labeled test split contains 2,419 generated images paired with 1,290 real images, and 1,168 of these real images can still be retrieved in their original form. As noted in [7], the generated images are PNG files while the real images are mostly JPEG files. To prevent the file format from separating the two classes, we use the compression fields provided by [7] and compress each generated image with the JPEG quality and chroma subsampling of its paired real image. MDMF uses 1,743 real images of the X-AIGD training split as its reference. AIDE and Effort are trained on the same data as MDMF with their official code (configurations in Appendix D.3). Cells report average AUROC over the 13 generators, and the ProGAN row of MDMF reports mean±std over the five runs with W = 32 in Table 10.
| Training data | MDMF | AIDE | Effort |
|---|---|---|---|
| ProGAN (same in Table 1) | 54.24±0.81 | 47.99 | 37.16 |
| SD v1.4 (same in Figure 3) | 85.28 | 72.17 | 81.02 |
With ProGAN training, all three detectors are close to or below chance on these generators, and MDMF obtains the highest AUROC of the three. The X-AIGD paper [3] also reports near-chance accuracy (48.6% to 52.1%) for the ProGAN-trained CNNspot, UnivFD and FatFormer. With SD v1.4 training, MDMF still outperforms AIDE and Effort. We have added these results, together with those on the published files without compression alignment, to Appendix E.1.
[7] Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection. arXiv 2026
[1/3] Rebuttal by Authors
Thank you for your time and constructive review. Here are our detailed replies.
R1: Thanks for the constructive comments. Section 2.3 builds on the deep-kernel test of [1] and the reference-based scoring of [2, 3], and Appendix C discusses patch-level classifiers [4] and PatchCraft [5], while a direct comparison of their design choices with MDMF was missing. We would like to reclaim that our work is novel in introducing a patch-level formulation of single-image detection, i.e., comparing the field of patch forensic signatures of one image with the fields of a population of real references. This has not been explored in previous local-artifact detectors [4–6], and has both conceptual and technical distinctions from them with significant knowledge advancement.
Conceptually, the local-artifact detectors [4–6] map local evidence to a real/fake decision with a trained classifier, whereas MDMF scores a test image by how far the field of its local evidence departs from the fields of real reference images. The table below summarizes the differences.
Technically, MDMF differs from the local-artifact detectors [4–6] in three aspects, and the first aspect also distinguishes MDMF from the deep-kernel MMD methods [1–3].
① Scalar patch signatures. A shared head maps each of the 49 pooled patch embeddings of an image to a scalar PFS, and the image is represented by the field of these signatures without image-level pooling or voting, whereas [1] uses a generic vector featurizer and [2, 3] use token or frame features.
② Test power on the patch field. The PFS head and the kernel are trained with the test-power objective of [1] on the fields of real and generated images (Eq. 5), whereas the local-artifact detectors [4–6] are trained with classification losses.
③ Scoring against real references. A test image is scored by the MMD between its field and a bank of real images (Eq. 6), whereas [4–6] score the image with a trained classifier.
Empirically, with the same frozen backbone and training data, an MMD objective on a global image-level output lowers the AUROC from 90.14 to 86.53, whereas the MMD objective of MDMF on the PFS field raises the AUROC from 93.22 to 95.65 (Table 2), which shows that the gain of the MMD objective depends on the PFS field. Direct combinations of DINOv2 with local patch learning or MMD also stay below the five-run average of MDMF (94.97, Table 10), namely pooling the patch signatures (at most 93.22, Table 7), classifying each patch and voting (at most 94.43 even with the best of eight patch thresholds, Table 16) and a generic deep-kernel featurizer on the same patches (91.87, Table 9). We have replaced "a new perspective" in the contribution statement of Section 1 with the patch-level formulation above, revised the first sentence of the conclusion accordingly, and added the comparison table to Appendix C.
[1] Learning Deep Kernels for Non-Parametric Two-Sample Tests. ICML 2020
[2] Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy. ICLR 2024
[3] Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection. NeurIPS 2025
[4] What Makes Fake Images Detectable? Understanding Properties that Generalize. ECCV 2020
[5] PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection. arXiv 2023
[6] Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection. CVPR 2024