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

• URL: http://arxiv.org/abs/2608.09158v1
• Date: Mon, 10 Aug 2026 06:09:50 GMT
• Title: From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
• Abstract summary: Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs.<n>This diversity includes low-frequency signals that are inaudible to humans but can still enter the model and influence its generation.<n>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.
• Score: 46.76277198630859
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals [0.0]
  We present the first controlled comparison of five neural-network architectures for gravitational-wave denoising.<n>We train identically across the full astrophysically-motivated spinning binary-black-hole parameter space.<n>A unifying principle emerges: matching network structure to the spectral anatomy of a coalescence outperforms brute-force model scaling.
  arXiv  Detail & Related papers  (2026-09-07T18:00:10Z)
• Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition [50.15288513086986]
  Contrastive decoding (CD) originally introduced to stabilize large language model (LLM)-based audio-visual speech recognition (AVSR) systems.<n>We propose reliability-aware scaling of CD for AVSR.
  arXiv  Detail & Related papers  (2026-08-26T08:25:15Z)
• S$^3$AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection [74.15663758681849]
  Single-stream framework integrates reliability-calibrated frequency adaptation into the adopted SAM backbone for MSOD.<n>Experiments on RGB-D, RGB-T, and RGB-NIR salient object detection benchmarks validate that the proposed framework achieves competitive performance.
  arXiv  Detail & Related papers  (2026-08-18T08:05:00Z)
• Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition [7.1200667451435296]
  This paper introduces the Whisper-Aware LLM, a framework that teaches an Audio-LLM to perceive and react to whispered speech.<n>Our model develops an intrinsic self-awareness by learning to quantify the physical deficiencies of acoustic signals.<n>The model sets a new state-of-the-art on whispered speech with a 17% relative CER reduction on AISHELL6-Whisper.
  arXiv  Detail & Related papers  (2026-08-11T12:02:55Z)
• UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization [13.738195795114516]
  We propose UniSkip-Mamba, a frequency-aware State Space Model framework that incorporates Unified Multimodal Sequence Fusion to preserve cross-modal phase relationships.<n>We achieve state-of-the-art (SOTA) performance: 63.4% AP@0.95 on LAV-DF and 63.58% mAP on AV-Deepfake1M, with 6x faster inference.
  arXiv  Detail & Related papers  (2026-07-05T20:51:24Z)
• How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding [4.852493246050006]
  Large language models (LLMs) generate outputs autoregressively, leading to inevitable output uncertainty.<n>We propose Log-Scale Focal Uncertainty (LSFU), a first-token-based metric inspired by focal loss.<n>We show UCPOF improves average accuracy by 6.03% over few-shot baselines, surpasses always-on full RAG by 5.75%, and reduces the average retrieval trigger rate by 50.66%.
  arXiv  Detail & Related papers  (2026-02-23T11:55:14Z)
• Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Data [57.85958428020496]
  Flow-Guided Neural Operator (FGNO) is a novel framework combining operator learning with flow matching for SSL training.<n>FGNO learns mappings in functional spaces by using Short-Time Fourier Transform to unify different time resolutions.<n>Unlike prior generative SSL methods that use noisy inputs during inference, we propose using clean inputs for representation extraction while learning representations with noise.
  arXiv  Detail & Related papers  (2026-02-12T18:54:57Z)
• Toward Noise-Aware Audio Deepfake Detection: Survey, SNR-Benchmarks, and Practical Recipes [2.5756681494057045]
  We present a framework that mixes MS-SNSD noises with ASVspoof 2021 DF utterances to evaluate under controlled signal-to-noise ratios (SNRs)<n>We study multi-condition training and fixed-SNR testing for pretrained encoders (WavLM, Wav2Vec2, MMS), reporting accuracy, ROC-AUC, and EER on binary and four-class (authenticity x corruption) tasks.
  arXiv  Detail & Related papers  (2025-12-15T02:22:37Z)
• SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection [6.042897432654865]
  Spectral-cONtrastive Audio Residuals (AR) is a frequency-guided framework for deepfake audio detectors.<n>AR disentangles an audio signal into complementary representations.<n> evaluated on the ASVspoof 2021 and in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2025-11-26T12:16:38Z)
• LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals [10.85580316542761]
  Hallucination remains a critical barrier for deploying large language models (LLMs) in reliability-sensitive applications.<n>We propose HSAD (Hidden Signal Analysis-based Detection), a novel hallucination detection framework that models the temporal dynamics of hidden representations.<n>Across multiple benchmarks, including TruthfulQA, HSAD achieves over 10 percentage points improvement compared to prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-16T15:08:19Z)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition [70.77292069313154]
  Large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF)
  arXiv  Detail & Related papers  (2024-02-08T07:21:45Z)
• SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models [76.43625653814911]
  Diffusion models have gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time. We introduce SURE-based MRI Reconstruction with Diffusion models (SMRD) to enhance robustness during testing.
  arXiv  Detail & Related papers  (2023-10-03T05:05:35Z)
• Learning based signal detection for MIMO systems with unknown noise statistics [84.02122699723536]
  This paper aims to devise a generalized maximum likelihood (ML) estimator to robustly detect signals with unknown noise statistics. In practice, there is little or even no statistical knowledge on the system noise, which in many cases is non-Gaussian, impulsive and not analyzable. Our framework is driven by an unsupervised learning approach, where only the noise samples are required.
  arXiv  Detail & Related papers  (2021-01-21T04:48:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.