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.
Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy
This paper introduces AI-MASLD, a stress-audit framework for medical LLMs that reveals how benchmark accuracy can hide serious safety failures, and demonstrates that open-weight models can match or exceed proprietary ones on safety dimensions.
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
This paper proposes DRL-CLBA, a clean label backdoor attack for speech classification using DDPG reinforcement learning and deep audio steganography, achieving high attack success rates and bypassing several defenses, exposing vulnerabilities in speech-controlled systems.
Coherent Context Can Silently Shift LLMs Into a Different Internal Regime — And Current Safety Systems Are Blind To It [D]
An independent researcher presents evidence that coherent context can shift LLMs into a different internal regime before producing output, bypassing surface-level safety filters. This suggests current alignment methods like RLHF may not be robust defenses.