Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis

Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains unclear how much jailbreak capability can arise from matched-text variation in speech delivery rather than from lexical rewriting or broader style transfer. We study this question by holding transcript content fixed and varying six speech-delivery pres…

Paper

Similar papers

© 2026 NYSGPT2525 LLC