Metraipolis › archive › dc_321eb06d9f09

A Federated Deepfake Speech Detection Method Based on Layer-Wise Center-Guided Weighting Aggregation — arXiv:2610.01259

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01259
License (as archived): CC0-1.0
Archived: 2026-10-07T12:38:38.858Z
SHA-256 of the archived text: 3ce544c21bb5f981efd446f69b0c06132ba77a15a6335cfa6f467cc0af9a1b36
Stable URL of this page: https://metraipolis.com/documento/dc_321eb06d9f09

How to cite

A Federated Deepfake Speech Detection Method Based on Layer-Wise Center-Guided Weighting Aggregation — arXiv:2610.01259 — arXiv (en), https://arxiv.org/abs/2610.01259 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_321eb06d9f09 (Metraipolis archive dc_321eb06d9f09, sha256 3ce544c21bb5f981efd446f69b0c06132ba77a15a6335cfa6f467cc0af9a1b36)

BibTeX

@misc{dc321eb06d9f09,
  title = {A Federated Deepfake Speech Detection Method Based on Layer-Wise Center-Guided Weighting Aggregation — arXiv:2610.01259},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01259},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_321eb06d9f09; sha256 3ce544c21bb5f981efd446f69b0c06132ba77a15a6335cfa6f467cc0af9a1b36},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01259. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The advancement of deep learning-based speech synthesis has significantly increased the diversity of deepfake speech, posing threats to voice authentication. While centralized training is effective for deepfake speech detection (DSD), it requires considerable computational resources and raises privacy concerns. To address these issues, we propose a Federated DSD (FedDSD) method that enables collaborative model training across decentralized speech datasets without sharing raw audio. Specifically, each client trains a local model using the FedProx algorithm to mitigate the effects of data heterogeneity and uploads model parameters to a central server. To improve global model aggregation, we further propose a layer-wise center-guided weighting aggregation (L-CGWA) strategy that adjusts each client's contribution per layer based on its distance to a reference center, capturing inter-client and inter-layer discrepancies and enhancing the robustness of model aggregation. Experimental results demonstrate that models trained under the proposed FedDSD method achieve equal error rates (EERs) comparable to those obtained via centralized co-training, while significantly out-performing models trained on individual corpora. Furthermore, the proposed FedDSD method demonstrates robust generalization capabilities across diverse cross-domain datasets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.01259 — 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 2026-10-07T12:11:28.576Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).