Paper

SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech

arXiv:2606.06037v1 Announce Type: cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evaluated on monolingual, text-based harmful prompts. This leaves their generalizability under multilingual and spoken settings, particularly code-switched speech, largely underexplored. To address this gap, we introduce SpeechJBB, an audio jailbreak dataset for benchmarking across multiple state-of-the-art LALMs. The extent of safety weaknesses is further probed by introducing an augmented setting where phono…

Authors:

Related discussions