Metraipolis › archive › dc_69d358316732

Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images — arXiv:2610.11706

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11706
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:26.967Z
SHA-256 of the archived text
398d1e56167540bc4328a93917785334b6a1466e4747663ac0962bbf1fab5a2f
Stable URL of this page
https://metraipolis.com/documento/dc_69d358316732

How to cite

Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images — arXiv:2610.11706 — arXiv (en), https://arxiv.org/abs/2610.11706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69d358316732 (Metraipolis archive dc_69d358316732, sha256 398d1e56167540bc4328a93917785334b6a1466e4747663ac0962bbf1fab5a2f)
BibTeX
@misc{dc69d358316732,
  title = {Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images — arXiv:2610.11706},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11706},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69d358316732; sha256 398d1e56167540bc4328a93917785334b6a1466e4747663ac0962bbf1fab5a2f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination inconsistencies improves detection. Temporal Self-Blended Images (T-SBI) transfer lighting statistics between frames of the same video, with the mismatch controlled by luminance difference ({\Delta}L). Using five training regimes and a three-seed comparison of high- and low-{\Delta}L training, we find no evidence of illumination-specific improvements. AUC differences remain within seed variability across four datasets, and an analysis of 506,328 attribute-binned samples shows no preferential reduction in errors under harsh lighting. Instead, T-SBI shifts prediction scores, changing optimal thresholds by approximately 0.34 on FaceForensics++ and 0.30 on Celeb-DF, making comparisons at a fixed threshold misleading. However, T-SBI improves robustness to heavy JPEG compression on DFDC (AUC 0.780 versus 0.696), potentially reflecting greater reliance on low-frequency cues. These findings highlight the importance of evaluating training methods against their intended targets and accounting for threshold effects.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.11706 — 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 2026-10-09T05:50:31.595Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).