Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Tune In, Act Up: Exploring the Impact of Audio Modality-Specific Edits on Large Audio Language Models in Jailbreak
23 Jan 2025
Abstract
Large Language Models (LLMs) demonstrate remarkable zero-shot performance
across various natural language processing tasks. The integration of multimodal
encoders extends their capabilities, enabling the development of Multimodal
Large Language Models that process vision, audio, and text. However, these
capabilities also raise significant security concerns, as these models can be
manipulated to generate harmful or inappropriate content through jailbreak.
While extensive research explores the impact of modality-specific input edits
on text-based LLMs and Large Vision-Language Models in jailbreak, the effects
of audio-specific edits on Large Audio-Language Models (LALMs) remain
underexplored. Hence, this paper addresses this gap by investigating how
audio-specific edits influence LALMs inference regarding jailbreak. We
introduce the Audio Editing Toolbox (AET), which enables audio-modality edits
such as tone adjustment, word emphasis, and noise injection, and the Edited
Audio Datasets (EADs), a comprehensive audio jailbreak benchmark. We also
conduct extensive evaluations of state-of-the-art LALMs to assess their
robustness under different audio edits. This work lays the groundwork for
future explorations on audio-modality interactions in LALMs security.
Metrics
12 Record Views
Details
- Title
- Tune In, Act Up: Exploring the Impact of Audio Modality-Specific Edits on Large Audio Language Models in Jailbreak
- Creators
- Erjia XiaoHao ChengJing ShaoJinhao DuanKaidi XuLe YangJindong GuRenjing Xu
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Other Identifier
- 991022020738404721