Metraipolis › archive › dc_344b151e56e2
GDBack: A Group-Delay Backdoor Attack on Speaker Identification via Analytic All-Pass Filtering — arXiv:2611.01721
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01721
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:55:24.629Z
- SHA-256 of the archived text
27f175ccff422d5db8cca455b59de8b383c887b4e0673391fe26f885206fd960- Stable URL of this page
https://metraipolis.com/documento/dc_344b151e56e2
How to cite
GDBack: A Group-Delay Backdoor Attack on Speaker Identification via Analytic All-Pass Filtering — arXiv:2611.01721 — arXiv (en), https://arxiv.org/abs/2611.01721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_344b151e56e2 (Metraipolis archive dc_344b151e56e2, sha256 27f175ccff422d5db8cca455b59de8b383c887b4e0673391fe26f885206fd960)
BibTeX
@misc{dc344b151e56e2,
title = {GDBack: A Group-Delay Backdoor Attack on Speaker Identification via Analytic All-Pass Filtering — arXiv:2611.01721},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01721},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_344b151e56e2; sha256 27f175ccff422d5db8cca455b59de8b383c887b4e0673391fe26f885206fd960},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing phase-based backdoor attacks on speaker identification rely on shared absolute phase patterns for cross-sample trigger consistency, while other audio backdoor attacks have explored shared transformations that produce input-dependent triggers. Whether phase-based triggers can achieve similar consistency without imposing identical output phase patterns remains unclear. We propose GDBack, a poison-only group-delay backdoor attack using cascaded second-order analytic all-pass filters. Applying a shared transformation across utterances ideally preserves spectral magnitude while introducing a consistent frequency-dependent phase response and group-delay contribution, without forcing identical output phases. Experiments on LibriSpeech and VoxCeleb1 with ECAPA-TDNN, x-vector, and RawNet3 achieve attack success rates above 94% across all six settings (97.00% on average), while maintaining benign accuracy close to clean models. Phase and magnitude interventions, inverse compensation, and parameter-sensitivity analyses support the role of the induced phase transformation in backdoor activation. Speech quality and content evaluations indicate limited perceptual and linguistic distortion, while robustness experiments, including real over-the-air tests, reveal varying effectiveness across conditions and architectures. These findings demonstrate that cross-sample trigger consistency can arise from a shared phase transformation without requiring a common absolute phase pattern. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2611.01721 — 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 2026-11-03T11:15:52.728Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).