LATIDIA · Ciberseguridad

Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability

arXiv:2610.31713v1 Anuncio Tipo: nuevo Resumen: Los avances en los modelos de lenguaje grandes omnimodales (OLLM) han permitido una interacción humano-IA cada vez más fluida, pero su procesamiento unificado de modalidades heterogéneas también

La noticia

arXiv:2610.31713v1 Announce Type: new Abstract: Advances in Omni-modal Large Language Models (OLLMs) have enabled increasingly seamless human-AI interaction, but their unified processing of heterogeneous modalities also expands the attack surface, allowing adversaries to exploit richer input compositions to circumvent safety alignment. To counter such risks, omni-modal guardrails have been proposed to detect and filter unsafe queries across arbitrary modalities. However, their capabilities and limitations remain insufficiently understood due to the absence of a comprehensive evaluation benchmark. In this paper, we present Omni-UBench, the first comprehensive framework for omni-modal safety assessment, evaluating guardrail models along three critical dimensions, i.e., safety, utility, and reliability. Omni-UBench curates over 183k samples drawn from 35+