arXiv cs.LG
· Papers
On Optimizing Multimodal Jailbreaks for Spoken Language Models
arXiv:2603.19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where adversarial prom