Metraipolis › archive › dc_2ae0e6132510
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI — arXiv:2608.28518
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28518
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:47:42.028Z
- SHA-256 of the archived text
104eebd7d449b3ae485a6ccdc5cf5362b5394a136d6e0d96fbb0c91e015e318f- Stable URL of this page
https://metraipolis.com/documento/dc_2ae0e6132510
How to cite
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI — arXiv:2608.28518 — arXiv (en), https://arxiv.org/abs/2608.28518 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ae0e6132510 (Metraipolis archive dc_2ae0e6132510, sha256 104eebd7d449b3ae485a6ccdc5cf5362b5394a136d6e0d96fbb0c91e015e318f)
BibTeX
@misc{dc2ae0e6132510,
title = {When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI — arXiv:2608.28518},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28518},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ae0e6132510; sha256 104eebd7d449b3ae485a6ccdc5cf5362b5394a136d6e0d96fbb0c91e015e318f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28518. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them preserve semantic structure but increase harmful ambiguity, while others weaken the model refusal behaviour and allow unsafe plans to be generated and executed. We show that in some cases automatic correction of ASR errors can reduce the risk, but this is not always effective. Overall, we show that ASR errors lead to significant safety risks for embodied AI. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.28518 — 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 2026-10-17T10:33:42.434Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).