Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models

• URL: http://arxiv.org/abs/2605.18168v1
• Date: Mon, 18 May 2026 10:10:31 GMT
• Title: Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
• Abstract summary: Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads.<n>We propose a new paradigm in which the role of audio shifts from content injection to safety alignment interference.<n>We show that interference audio, benign in content but infused with specific ALS, can serve as a universal jailbreak trigger.
• Score: 29.672999404488838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to embed harmful content into the audio signal. In this work, we challenge this necessity and propose a new paradigm in which the role of audio shifts from content injection to safety alignment interference. We reveal that LALM safety alignment can be compromised solely by specific Acoustic Latent Semantics (ALS), the underlying paralinguistic features intrinsic to the priors of audio generative models. Distinct from previous works that leverage explicit acoustic parameters to merely style malicious audio, we demonstrate that interference audio, benign in content but infused with specific ALS, can serve as a universal jailbreak trigger. Leveraging this insight, we propose the Acoustic Interference Attack (AIA), which decouples the attack payload from the audio. Specifically, AIA employs a set of universal, instruction-neutral interference audio, enabling standard malicious text queries to bypass safety alignment without instance-specific optimization. Extensive experiments on 10 LALMs across five datasets demonstrate that AIA achieves the state-of-the-art attack success rate. Furthermore, our interpretability analysis uncovers the inference path drift induced by AIA and identifies the inherent effective patterns within ALS, revealing the fundamental vulnerability of cross-modal alignment in LALMs.

Related papers

• Acoustically Grounded Cost Learning for Open-Vocabulary Audio-Visual Semantic Segmentation [95.88527433039519]
  Open-Vocabulary Audio-Visual Semantic (OV-AVSS) aims to perform pixel-level segmentation of sound-emitting objects from an open set of categories.<n>We reformulate the objective to be category-specific and propose a novel Acoustically Grounded Cost Learning framework.<n>Experiments on the AVSBench-OV dataset demonstrate that our method significantly outperforms previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-08-29T08:02:27Z)
• Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation [16.72528638767562]
  Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline.<n>This paper provides a unified taxonomy and a controlled empirical evaluation of LALM jailbreak attacks and defenses.
  arXiv  Detail & Related papers  (2026-05-28T14:53:27Z)
• Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions [52.45054413627452]
  TPI-Train is a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling.<n>TPI-Bench is a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy.
  arXiv  Detail & Related papers  (2026-04-19T10:03:42Z)
• Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs [19.239722054750832]
  We present the first systematic study of benign fine-tuning safety in Audio LLMs.<n>We show that benign fine-tuning elevates Jailbreak Success Rate (JSR) from single digits to as high as 87.12%.<n>We propose two defenses: filtering training data to maximize distance from harmful embeddings, and a textual system prompt at inference.
  arXiv  Detail & Related papers  (2026-04-17T19:28:07Z)
• Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection [22.306688903148046]
  Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text.<n>We propose textitAudioHijack, a framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs.<n>Experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 categories misbehavior.
  arXiv  Detail & Related papers  (2026-04-16T04:22:11Z)
• Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs [53.41256816230278]
  Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion.<n>While excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception.<n>We propose Unified Audio (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components.
  arXiv  Detail & Related papers  (2026-04-14T09:30:12Z)
• Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs [38.35295248094619]
  Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels.<n>We present Sirens' Whisper, the first practical framework for covert prompt-based attacks against speech-driven LLMs.<n>SWhisper enables robust, inaudible delivery of arbitrary target baseband audio-including long and structured prompts-on commodity devices.
  arXiv  Detail & Related papers  (2026-03-14T09:01:48Z)
• SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models [49.313324100819955]
  Signal Embedding Energy (SEE) is a method for quantifying the impact of noise intensity on LALM inputs.<n>SEE exhibits a strong correlation with LALM performance, achieving a correlation of 0.98.<n>This paper introduces a novel metric for noise quantification in LALMs, providing guidance for robustness improvements in real-world deployments.
  arXiv  Detail & Related papers  (2026-01-12T08:57:55Z)
• ENJ: Optimizing Noise with Genetic Algorithms to Jailbreak LSMs [61.09812971042288]
  Evolutionary Noise Jailbreak (ENJ)<n>This paper proposes a genetic algorithm to transform environmental noise from a passive interference into an actively optimizable attack carrier for jailbreaking LSMs.<n>Experiments on multiple mainstream speech models show that ENJ's attack effectiveness is significantly superior to existing baseline methods.
  arXiv  Detail & Related papers  (2025-09-14T06:39:38Z)
• Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers [40.4026420070893]
  We introduce Hidden in the Noise (HIN), a novel backdoor attack framework designed to exploit subtle, audio-specific features.<n>HIN applies acoustic modifications to raw audio waveforms, such as alterations to temporal dynamics and strategic injection of spectrally tailored noise.<n>To evaluate ALLM robustness against audio-feature-based triggers, we develop the AudioSafe benchmark, assessing nine distinct risk types.
  arXiv  Detail & Related papers  (2025-08-04T08:15:16Z)
• From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
  Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-26T16:08:41Z)
• Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models [50.89022445197919]
  Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs)<n>Recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment.
  arXiv  Detail & Related papers  (2025-05-26T08:25:25Z)
• Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models [19.373533532464915]
  We introduce AJailBench, the first benchmark specifically designed to evaluate jailbreak vulnerabilities in LAMs.<n>We use this dataset to evaluate several state-of-the-art LAMs and reveal that none exhibit consistent robustness across attacks.<n>Our findings demonstrate that even small, semantically preserved perturbations can significantly reduce the safety performance of leading LAMs.
  arXiv  Detail & Related papers  (2025-05-21T11:47:47Z)

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.