Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models

• URL: http://arxiv.org/abs/2501.13772v3
• Date: Sun, 01 Jun 2025 16:57:27 GMT
• Title: Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
• Authors: Hao Cheng, Erjia Xiao, Jing Shao, Yichi Wang, Le Yang, Chao Shen, Philip Torr, Jindong Gu, Renjing Xu,
• Abstract summary: Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks.<n>Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large Language Models (MLLMs) that process not only text but also visual and auditory modality inputs.<n>These advanced capabilities may also pose significant security risks, as models can be exploited to generate harmful or inappropriate content through jailbreak attack.
• Score: 35.884976768636726
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks. Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large Language Models (MLLMs) that process not only text but also visual and auditory modality inputs. However, these advanced capabilities may also pose significant security risks, as models can be exploited to generate harmful or inappropriate content through jailbreak attack. While prior work has extensively explored how manipulating textual or visual modality inputs can circumvent safeguards in LLMs and MLLMs, the vulnerability of audio-specific Jailbreak on Large Audio-Language Models (LALMs) remains largely underexplored. To address this gap, we introduce \textbf{Jailbreak-AudioBench}, which consists of the Toolbox, curated Dataset, and comprehensive Benchmark. The Toolbox supports not only text-to-audio conversion but also various editing techniques for injecting audio hidden semantics. The curated Dataset provides diverse explicit and implicit jailbreak audio examples in both original and edited forms. Utilizing this dataset, we evaluate multiple state-of-the-art LALMs and establish the most comprehensive Jailbreak benchmark to date for audio modality. Finally, Jailbreak-AudioBench establishes a foundation for advancing future research on LALMs safety alignment by enabling the in-depth exposure of more powerful jailbreak threats, such as query-based audio editing, and by facilitating the development of effective defense mechanisms.

Related papers

• 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)
• Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework [6.002582335323663]
  We present an adversarial attack targeting the speech input of aligned Multimodal Large Language Models (MLLMs) in a white box scenario.<n>We introduce a novel token level attack that leverages access to the model's speech tokenization to generate adversarial token sequences.<n>Our approach achieves up to 89 percent attack success rate across multiple restricted tasks.
  arXiv  Detail & Related papers  (2025-05-24T20:46:36Z)
• JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models [25.93179924805564]
  We present JALMBench, the textitfirst comprehensive benchmark to assess the safety of Audio Language Models (ALMs) against jailbreak attacks.<n>Using JALMBench, we provide an in-depth analysis of attack efficiency, topic sensitivity, voice diversity, and attack representations.
  arXiv  Detail & Related papers  (2025-05-23T07:29:55Z)
• 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)
• Multilingual and Multi-Accent Jailbreaking of Audio LLMs [19.5428160851918]
  Multi-AudioJail is the first systematic framework to exploit multilingual and multi-accent audio jailbreaks.<n>We show how acoustic perturbations interact with cross-lingual phonetics to cause jailbreak success rates to surge.<n>We plan to release our dataset to spur research into cross-modal defenses.
  arXiv  Detail & Related papers  (2025-04-01T18:12:23Z)
• "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models [0.9480364746270077]
  This paper explores audio jailbreaks targeting Audio-Language Models (ALMs) We construct adversarial perturbations that generalize across prompts, tasks, and even base audio samples. We analyze how ALMs interpret these audio adversarial examples and reveal them to encode imperceptible first-person toxic speech.
  arXiv  Detail & Related papers  (2025-02-02T08:36:23Z)
• Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models [50.89022445197919]
  We show that open-source audio LMMs suffer an average attack success rate of 69.14% on harmful audio questions. Our speech-specific jailbreaks on Gemini-1.5-Pro achieve an attack success rate of 70.67% on the harmful query benchmark.
  arXiv  Detail & Related papers  (2024-10-31T12:11:17Z)
• Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models [0.9285295512807729]
  The Audio Question Answering (AQA) task includes audio event classification, audio captioning, and open-ended reasoning.<n>LALMs excel in general audio understanding, but are limited in temporal reasoning.<n>This paper addresses these challenges and limitations in audio temporal reasoning.
  arXiv  Detail & Related papers  (2024-09-10T05:26:53Z)
• Investigating Decoder-only Large Language Models for Speech-to-text Translation [39.17113782374464]
  Large language models (LLMs) are known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains. We propose a decoder-only architecture that enables the LLM to directly consume the encoded speech representation and generate the text translation. Our model achieves state-of-the-art performance on CoVoST 2 and FLEURS among models trained without proprietary data.
  arXiv  Detail & Related papers  (2024-07-03T14:42:49Z)
• Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings [57.136748215262884]
  We introduce ObscurePrompt for jailbreaking LLMs, inspired by the observed fragile alignments in Out-of-Distribution (OOD) data.<n>We first formulate the decision boundary in the jailbreaking process and then explore how obscure text affects LLM's ethical decision boundary.<n>Our approach substantially improves upon previous methods in terms of attack effectiveness, maintaining efficacy against two prevalent defense mechanisms.
  arXiv  Detail & Related papers  (2024-06-19T16:09:58Z)
• Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models [49.87432626548563]
  We introduce methods to assess the extent of object hallucination of publicly available LALMs. Our findings reveal that LALMs are comparable to specialized audio captioning models in their understanding of audio content. We explore the potential of prompt engineering to enhance LALMs' performance on discriminative questions.
  arXiv  Detail & Related papers  (2024-06-12T16:51:54Z)
• AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations [1.2101820447447276]
  Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Our method systematically generates audio-caption pairs by augmenting audio clips with natural language labels and corresponding audio signal processing operations. This scalable method produces AudioSetMix, a high-quality training dataset for text-and-audio related models.
  arXiv  Detail & Related papers  (2024-05-17T21:08:58Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• Jailbreaking Attack against Multimodal Large Language Model [69.52466793164618]
  This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs) A maximum likelihood-based algorithm is proposed to find an emphimage Jailbreaking Prompt (imgJP) Our approach exhibits strong model-transferability, as the generated imgJP can be transferred to jailbreak various models.
  arXiv  Detail & Related papers  (2024-02-04T01:29:24Z)
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models [98.34889301515412]
  We develop the Qwen-Audio model and address the limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types. Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning. We further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.
  arXiv  Detail & Related papers  (2023-11-14T05:34:50Z)
• AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs [27.122094554340194]
  We extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities. The resulting end-to-end model, named AudioChatLlama, can utilize audio prompts as a replacement for text and sustain a conversation.
  arXiv  Detail & Related papers  (2023-11-12T06:56:14Z)
• LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT [65.69648099999439]
  Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks. We propose LauraGPT, a novel unified audio-and-text GPT-based LLM for audio recognition, understanding, and generation.
  arXiv  Detail & Related papers  (2023-10-07T03:17:59Z)
• Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning [50.28566759231076]
  We propose an innovative, automatic approach to establish an audio dataset with high-quality captions. Specifically, we construct a large-scale, high-quality, audio-language dataset, named as Auto-ACD, comprising over 1.5M audio-text pairs. We employ LLM to paraphrase a congruent caption for each audio, guided by the extracted multi-modality clues.
  arXiv  Detail & Related papers  (2023-09-20T17:59:32Z)
• Prompting Large Language Models with Speech Recognition Abilities [31.77576008965215]
  We extend the capabilities of large language models by directly attaching a small audio encoder allowing it to perform speech recognition. Experiments on MultilingualSpeech show that incorporating a conformer encoder into the open sourced LLaMA-7B allows it to outperform monolingual baselines by 18%.
  arXiv  Detail & Related papers  (2023-07-21T08:39:15Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)

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.