Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs
多模态大模型在不同语言与模态下呈现截然不同的脆弱性,为AI安全防御提供关键新视角。
arXiv:2605.23157v1 Announce Type: new Abstract: The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reve…