Metraipolis › archive › dc_fd83a6d1dbee

Breaking Adversarial Transferability in Fine-Tuned Speech Recognition — arXiv:2610.09109

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09109
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:22.774Z
SHA-256 of the archived text
2735258f445a4cedaa0263feaa006f76e66b333e849d192e63149e9ae8e1e822
Stable URL of this page
https://metraipolis.com/documento/dc_fd83a6d1dbee

How to cite

Breaking Adversarial Transferability in Fine-Tuned Speech Recognition — arXiv:2610.09109 — arXiv (en), https://arxiv.org/abs/2610.09109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd83a6d1dbee (Metraipolis archive dc_fd83a6d1dbee, sha256 2735258f445a4cedaa0263feaa006f76e66b333e849d192e63149e9ae8e1e822)
BibTeX
@misc{dcfd83a6d1dbee,
  title = {Breaking Adversarial Transferability in Fine-Tuned Speech Recognition — arXiv:2610.09109},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09109},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd83a6d1dbee; sha256 2735258f445a4cedaa0263feaa006f76e66b333e849d192e63149e9ae8e1e822},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protection. We show this assumption is fragile: adversarial perturbations crafted on the public base model transfer effectively to fine-tuned target models, severely degrading performance and posing concerns for safety-critical applications. We propose TransferBreaker, a unified fine-tuning framework that suppresses adversarial transfer by integrating Base Adversarial Fine-Tuning, which restricts adversarial training to base-effective perturbations; Latent Jacobian Regularization, which enforces latent-space invariance by suppressing adversarially sensitive directions; and HybridGrad-AFT, which improves robustness against adaptive attacks by interpolating transferable perturbations from base and target gradients. We theoretically justify all components and evaluate TransferBreaker across three languages and four large ASR models, reducing adversarial WER from 92.6 to 27.8. Our code is publicly available at this https URL .

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/2610.09109 — 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 2026-10-08T10:50:37.656Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).