Metraipolis › archive › dc_e11bdc29438e

Understanding Why Foundation Models Work for Diffusion-Generated Image Detection — arXiv:2608.12155

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12155
License (as archived)
CC0-1.0
Archived
2026-10-19T05:49:40.152Z
SHA-256 of the archived text
33783fcca3fece6ad7f392b969c1fe771460baee63b9997014fe2267463b950e
Stable URL of this page
https://metraipolis.com/documento/dc_e11bdc29438e

How to cite

Understanding Why Foundation Models Work for Diffusion-Generated Image Detection — arXiv:2608.12155 — arXiv (en), https://arxiv.org/abs/2608.12155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e11bdc29438e (Metraipolis archive dc_e11bdc29438e, sha256 33783fcca3fece6ad7f392b969c1fe771460baee63b9997014fe2267463b950e)
BibTeX
@misc{dce11bdc29438e,
  title = {Understanding Why Foundation Models Work for Diffusion-Generated Image Detection — arXiv:2608.12155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e11bdc29438e; sha256 33783fcca3fece6ad7f392b969c1fe771460baee63b9997014fe2267463b950e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision foundation models have recently emerged as powerful feature extractors for detecting AI-generated images, achieving strong generalization across generators and robustness to common image degradations. However, the reason behind their effectiveness is poorly understood. In this work, we investigate what cues are exploited by foundation-model-based detectors to distinguish real images from diffusion-generated ones. To this end, we design an ad hoc analysis protocol based on DDIM inversion. Given a real image we generate a sequence of synthetic copies by changing the depth of DDIM inversion. Even though most copies are semantically identical to the real reference, the detector score varies significantly across them due to subtle traces introduced by the diffusion synthesis, showing that its decision is not primarily driven by semantic failures. Through a frequency-swapping analysis, we further reveal that the discriminative cues exploited by the detectors are mainly localized in the low-to-mid frequency range, rather than only in the high-frequency range, as is the case for artifacts commonly associated with generative models. Finally, a latent-space analysis shows that regenerated images exhibit reduced variance and effective dimensionality, indicating that diffusion models do not fully reproduce the variability of real data. Overall, our results suggest that foundation-model-based detectors succeed by capturing non-semantic low-to-mid frequency distributional discrepancies between real and diffusion-generated images. These findings provide new insight into the robustness and generalization of such detectors and suggest directions for more interpretable forensic methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12155 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:42:25.912Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).