OmniGuard：统一的多模态防护机制与刻意推理
OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
AI总结：
OmniGuard通过统一的多模态防护机制与刻意推理能力，有效提升多模态安全防护的鲁棒性和泛化能力。
摘要：
多模态大语言模型（OLLMs）能够处理文本、图像、视频和音频，这为人类与AI交互中的安全性和价值防护带来了新的挑战。以往的防护研究大多针对单模态设置，通常将保护措施框架为二元分类，这限制了在多样化模态和任务中的鲁棒性。为解决这一差距，我们提出了OmniGuard，这是首个多模态防护机制家族，能够通过刻意推理能力在所有模态中执行保护措施。为了支持OMNIGUARD的训练，我们精心编纂了一个大规模、全面的多模态安全数据集，包含超过21万种多样化的样本，输入涵盖了所有模态通过单模态和跨模态样本。每个样本都带有结构化的安全标签和经过精心编排的安全批评，这些批评由专家模型通过有针对性的蒸馏生成。在15个基准测试中进行的广泛实验表明，OmniGuard在广泛的多模态安全场景中实现了强大的效果和泛化能力。重要的是，OmniGuard提供了一个统一的框架，能够在多模态中实施政策并缓解风险，为构建更加稳健和有能力的多模态防护系统铺平了道路。
英文摘要：
Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal settings and typically frames safeguarding as binary classification, which limits robustness across diverse modalities and tasks. To address this gap, we propose OmniGuard, the first family of omni-modal guardrails that performs safeguarding across all modalities with deliberate reasoning ability. To support the training of OMNIGUARD, we curate a large, comprehensive omni-modal safety dataset comprising over 210K diverse samples, with inputs that cover all modalities through both unimodal and cross-modal samples. Each sample is annotated with structured safety labels and carefully curated safety critiques from expert models through targeted distillation. Extensive experiments on 15 benchmarks show that OmniGuard achieves strong effectiveness and generalization across a wide range of multimodal safety scenarios. Importantly, OmniGuard provides a unified framework that enforces policies and mitigates risks in omni-modalities, paving the way toward building more robust and capable omnimodal safeguarding systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
