# From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs

arXiv: https://arxiv.org/abs/2608.09158 · HTML: https://mlsanity.com/paper/2608.09158/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [DolphinAtack: Inaudible Voice Commands](https://mlsanity.com/paper/1708.09537/) (2017)
- [CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition](https://mlsanity.com/paper/1801.08535/) (2018)
- [Speech Denoising with Deep Feature Losses](https://mlsanity.com/paper/1806.10522/) (2018)
- [Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard](https://mlsanity.com/paper/2511.10222/) (2025)
- [Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models](https://mlsanity.com/paper/2405.06134/) (2024)
- [Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study](https://mlsanity.com/paper/2505.19598/) (2025)
- [Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers](https://mlsanity.com/paper/2508.02175/) (2025)
- [Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs](https://mlsanity.com/paper/2505.14286/) (2025)

## Abstract (arXiv)

Large 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.