Tune In, Act Up: Exploring the Impact of Audio Modality-Specific Edits on Large Audio Language Models in Jailbreak (2501.13772v1)

Abstract: 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 LLMs 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-LLMs in jailbreak, the effects of audio-specific edits on Large Audio-LLMs (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.