titleFrom Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
authorsYuanhe Zhang, Weiliu Wang, Jie Ren, Liang Lin, Zhenhong Zhou, Haoran Gao, Kun Wang, Chen Li, Li Sun, Sen Su
date2026-08-10
venuearXiv (preprint, not peer reviewed)
idarXiv:2608.09158
upvotes2 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
abstractLarge audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs. This diversity includes low-frequency signals that are inaudible to humans but can still enter the model and influence its generation. However, the practical impact of such low-frequency inputs on LALMs remains largely unexplored. In this paper, we propose Intermittent Low-Frequency Lockout (ILL), an inaudible red teaming method that evaluates this risk using a universal waveform template in a black box setting. ILL uses Sentence Attention Scale Estimation to determine active intervals and Frequency Confusion Transfer to construct a low-frequency waveform with continuous phase from corpus spectral variation. To mitigate this risk, we propose Distributional Requery Guard (DRG) to detect low-frequency distribution shifts and conditionally request a second recording for semantic recovery. Across six LALMs and multiple audio understanding tasks, ILL reduces accuracy by up to 67 percentage points while receiving a mean human audibility rating of 1.33, close to 1.17 for clean audio; DRG raises mean attacked accuracy from 28.5\% to 46.1\% after clean reacquisition. These findings identify a previously overlooked safety risk for LALMs and provide a foundation for future research on robust audio understanding.

cite

@misc{zhang2026from,
  title={From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs},
  author={Yuanhe Zhang and Weiliu Wang and Jie Ren and Liang Lin and Zhenhong Zhou and Haoran Gao and Kun Wang and Chen Li and Li Sun and Sen Su},
  year={2026},
  eprint={2608.09158},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.09158}
}