From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
Summary
A paper introducing ILL, an inaudible low-frequency red-teaming method to expose safety vulnerabilities in audio-language models, and DRG, a defense that detects distribution shifts and requests a second recording to recover accuracy.
View Cached Full Text
Cached at: 08/14/26, 03:29 PM
Paper page - From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
Source: https://huggingface.co/papers/2608.09158
Abstract
Researchers propose a black-box red-teaming method using inaudible low-frequency waveforms to expose vulnerabilities in audio-language models, alongside a defense that detects distribution shifts and requests a second recording to recover accuracy.
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 proposeIntermittent Low-Frequency Lockout(ILL), an inaudible red teaming method that evaluates this risk using a universal waveform template in a black box setting. ILL usesSentence Attention Scale Estimationto determine active intervals andFrequency Confusion Transferto construct a low-frequency waveform with continuous phase from corpus spectral variation. To mitigate this risk, we proposeDistributional 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.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2608\.09158
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.09158 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.09158 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.09158 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
A comprehensive survey reviewing the trustworthiness challenges of Large Audio Language Models (LALMs), including vulnerabilities like cross-modal jailbreaking and acoustic backdoors, and proposing a defense-in-depth roadmap.
Voice AI Systems Are Vulnerable to Hidden Audio Attacks
New research shows that imperceptible audio signals can hijack large audio-language models (LALMs) with 79-96% success, forcing them to execute unauthorized commands like web searches or sending emails. The technique, dubbed AudioHijack, targets generative models and works regardless of user input, posing a serious security risk to voice AI systems.
The Implications of Linguistic Illegibility for LLM Security
The paper introduces linguistic illegibility in large language models, arguing that security mechanisms relying on linguistic self-reporting are flawed and proposes taint tracking and sandboxing as more robust alternatives.
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
This paper proposes using lightweight MLP probes on activations from LLaMA-3.1-8B to detect harmful prompts with high F1 scores, offering a cost-effective alternative to large external guardrail models.
Audio LLMs Know When They Can't Hear You
This paper investigates whether audio large language models can detect unreliable transcriptions and proposes a lightweight predictor using audio encoder representations to trigger clarification requests.