Metraipolis › archive › dc_f804ebe4ef3f

Backdooring Acoustic Foundation Models for Physically Realizable Triggers — arXiv:2610.09819

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09819
License (as archived)
CC0-1.0
Archived
2026-10-08T12:37:07.087Z
SHA-256 of the archived text
8af4f5933fa28b7a5968f508ce386d0b6d54867a4ab6870929d7c72e5e2ea4a0
Stable URL of this page
https://metraipolis.com/documento/dc_f804ebe4ef3f

How to cite

Backdooring Acoustic Foundation Models for Physically Realizable Triggers — arXiv:2610.09819 — arXiv (en), https://arxiv.org/abs/2610.09819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f804ebe4ef3f (Metraipolis archive dc_f804ebe4ef3f, sha256 8af4f5933fa28b7a5968f508ce386d0b6d54867a4ab6870929d7c72e5e2ea4a0)
BibTeX
@misc{dcf804ebe4ef3f,
  title = {Backdooring Acoustic Foundation Models for Physically Realizable Triggers — arXiv:2610.09819},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09819},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f804ebe4ef3f; sha256 8af4f5933fa28b7a5968f508ce386d0b6d54867a4ab6870929d7c72e5e2ea4a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this gap by proposing the Foundation Acoustic model Backdoor (FAB) attack, demonstrating that state-of-the-art AFMs are susceptible to backdooring under practical settings. Despite making minimal assumptions about adversary capabilities (e.g., no access to pre-training data), we show that FAB preserves benign performance while inducing backdoors that survive fine-tuning and cause significant degradation across diverse downstream tasks when activated. Notably, FAB utilizes task-agnostic, physically realizable, inconspicuous, and sync-free triggers (e.g., a background siren). We evaluate FAB using two leading AFMs, nine downstream tasks, and four different triggers. We further demonstrate its effectiveness against established defenses and across both digital and physical domains. While extensive end-to-end fine-tuning can mitigate FAB, such a defense is resource-intensive and task-specific. Our work highlights critical risks to AFMs and calls for advanced defenses.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.09819 — 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 2026-10-08T12:14:15.421Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).