Metraipolis › archive › dc_486a9fd3ffb4

DFD-Lab: A Modular Audio-Visual Deepfake Detection Pipeline — arXiv:2609.23830

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23830
License (as archived)
CC0-1.0
Archived
2026-10-09T22:04:40.791Z
SHA-256 of the archived text
46e402ba3c135ba401a3786a7499b82d9be9edd4226554579fb95fe55c8fe489
Stable URL of this page
https://metraipolis.com/documento/dc_486a9fd3ffb4

How to cite

DFD-Lab: A Modular Audio-Visual Deepfake Detection Pipeline — arXiv:2609.23830 — arXiv (en), https://arxiv.org/abs/2609.23830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_486a9fd3ffb4 (Metraipolis archive dc_486a9fd3ffb4, sha256 46e402ba3c135ba401a3786a7499b82d9be9edd4226554579fb95fe55c8fe489)
BibTeX
@misc{dc486a9fd3ffb4,
  title = {DFD-Lab: A Modular Audio-Visual Deepfake Detection Pipeline — arXiv:2609.23830},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23830},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_486a9fd3ffb4; sha256 46e402ba3c135ba401a3786a7499b82d9be9edd4226554579fb95fe55c8fe489},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Comparing audio-visual deepfake detectors requires coordinating dataset adaptation, temporal input representation, model interfaces and experimental conditions. We present DFD-Lab, a modular pipeline that separates these responsibilities while supporting shared training and evaluation workflows. We integrate three implementations: Xception-based maximum-logit fusion, ResNet with temporal LSTM fusion, and our AVFF reimplementation. Experiments cover external testing, degradation-based training augmentation and evaluation-time corruption. On a filtered subset of Deepfake-Eval-2024, models trained on FakeAVCeleb attain baseline AUROC values of 0.504, 0.538 and 0.458. JPEG50 training augmentation raises these to 0.691, 0.605 and 0.570, respectively, while all three accuracies decrease. These results illustrate why training interventions, evaluation corruptions and metric-dependent outcomes should remain distinct within a common pipeline. The contribution is the integration of audio-visual processing, interchangeable detectors and configurable experimental workflows, supported by empirical case studies. The findings highlight the challenge of cross-dataset detection and the complementary information provided by ranking and classification metrics.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.23830 — 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 2026-10-09T21:45:20.959Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).