Metraipolis › archive › dc_b75bd9ce25fb

Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection — arXiv:2610.39483

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39483
License (as archived)
CC0-1.0
Archived
2026-10-31T06:09:19.802Z
SHA-256 of the archived text
6d7bc9d1b15dd7e2022313d2f77a28b64b349ecd51d5852c9403abcada8835a0
Stable URL of this page
https://metraipolis.com/documento/dc_b75bd9ce25fb

How to cite

Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection — arXiv:2610.39483 — arXiv (en), https://arxiv.org/abs/2610.39483 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b75bd9ce25fb (Metraipolis archive dc_b75bd9ce25fb, sha256 6d7bc9d1b15dd7e2022313d2f77a28b64b349ecd51d5852c9403abcada8835a0)
BibTeX
@misc{dcb75bd9ce25fb,
  title = {Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection — arXiv:2610.39483},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39483},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b75bd9ce25fb; sha256 6d7bc9d1b15dd7e2022313d2f77a28b64b349ecd51d5852c9403abcada8835a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39483. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organizations, putting privacy and the transparency demanded by forensic review in direct conflict. Federated learning resolves the privacy side by sharing only model updates rather than raw data, but whether this comes at the cost of trustworthy gradient-based explanations, which analysts rely on to decide whether or not to trust a flagged clip, has not been studied. We present the systematic study of Grad-CAM explanation faithfulness under federated deepfake detection, evaluating an EfficientNet-B4 detector on FaceForensics++ across five federated clients under varying degrees of data heterogeneity. We find that the relationship between federation and explanation quality is non-monotonic: at near-IID (Independent and Identically Distributed Data) and moderate heterogeneity, federated models match or exceed the faithfulness of a centralized baseline, but at extreme heterogeneity, explanations break down entirely, becoming spatially incoherent and, on average, causally misleading. This degradation is not a general cost of federated training but a threshold effect tied to client heterogeneity, and we offer practical guidance for identifying when privacy-preserving deepfake detection can be deployed safely and when its explanations can no longer be trusted. Code and data partitions are available for reproducibility.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39483 — 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 2026-10-31T06:07:08.524Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).