Metraipolis › archive › dc_e104984dfb21
CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection — arXiv:2609.19818
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19818
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:23:37.451Z
- SHA-256 of the archived text
e62db4917e99af54266e6e5bd53ae5195765889b7fc0c18c6861a6b93f1e7635- Stable URL of this page
https://metraipolis.com/documento/dc_e104984dfb21
How to cite
CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection — arXiv:2609.19818 — arXiv (en), https://arxiv.org/abs/2609.19818 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e104984dfb21 (Metraipolis archive dc_e104984dfb21, sha256 e62db4917e99af54266e6e5bd53ae5195765889b7fc0c18c6861a6b93f1e7635)
BibTeX
@misc{dce104984dfb21,
title = {CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection — arXiv:2609.19818},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19818},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e104984dfb21; sha256 e62db4917e99af54266e6e5bd53ae5195765889b7fc0c18c6861a6b93f1e7635},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19818. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalizing to unseen attacks remains challenging for audio deepfake detectors, and collecting training data covering all potential attacks is impractical. We explore recurrent refinement in an already-trained SSL-based detector without additional data or changes to its original parameters. However, directly recycling encoder outputs as inputs degrades detection in our diagnostic. We propose CoReLoop, which makes this reuse effective by adapting recurrent inputs to the frozen encoder, controlling state updates, and aligning refined outputs with the frozen classifier. By training only lightweight refinement modules and loop-specific low-rank adapters on the original data, CoReLoop enables additional refinement while preserving the detector's original first-pass prediction. On 14 cross-domain test sets, the 24-layer model reduces pooled equal error rate (EER) from 4.85% to 3.74% with two passes, with approximately 10M trainable parameters out of 598M. To selectively apply this refinement, an optional halting head chooses the depth for each utterance, achieving 3.73% pooled EER with an average of 1.18 passes. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.19818 — 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 2026-10-10T03:04:13.853Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).