Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911411912835072 |
|---|---|
| author | Yu, Ye Jin, Haibo Yu, Yaoning Zhuang, Jun Wang, Haohan |
| author_facet | Yu, Ye Jin, Haibo Yu, Yaoning Zhuang, Jun Wang, Haohan |
| contents | Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We examine the security implications of this modality shift by designing a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. The attack leverages an advanced instruction-following text-to-speech (TTS) model to exploit structural and acoustic properties, thereby circumventing safety mechanisms primarily calibrated for text. When delivered through synthetic speech, the narrative format elicits restricted outputs from state-of-the-art models, including Gemini 2.0 Flash, achieving a 98.26% success rate that substantially exceeds text-only baselines. These results highlight the need for safety frameworks that jointly reason over linguistic and paralinguistic representations, particularly as speech-based interfaces become more prevalent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_23255 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models Yu, Ye Jin, Haibo Yu, Yaoning Zhuang, Jun Wang, Haohan Computation and Language Artificial Intelligence Cryptography and Security Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We examine the security implications of this modality shift by designing a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. The attack leverages an advanced instruction-following text-to-speech (TTS) model to exploit structural and acoustic properties, thereby circumventing safety mechanisms primarily calibrated for text. When delivered through synthetic speech, the narrative format elicits restricted outputs from state-of-the-art models, including Gemini 2.0 Flash, achieving a 98.26% success rate that substantially exceeds text-only baselines. These results highlight the need for safety frameworks that jointly reason over linguistic and paralinguistic representations, particularly as speech-based interfaces become more prevalent. |
| title | Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2601.23255 |