VMD-FACT：一个用于检测真实感AI生成视频虚假信息的新视频数据集与基于多模态大语言模型的方法
VMD-FACT: A New Video Dataset and MLLM-based method for Detecting Realistic AI-Generated Video Misinformation
该工作提出的RAVM数据集和IEEG模型为检测AI生成视频虚假信息提供了新基准和可解释方法，视觉研究者可借鉴其证据图构建和跨模态一致性分析思路，用于视频真实性验证和多模态推理任务。
原文依据 we introduce RAVM: the first Realistic AI-Generated Video Misinformation Detection Dataset
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式AI的快速发展，包括Sora等模型，加剧了视频虚假信息的威胁。检测这些AI生成的视频虚假信息的一个关键挑战在于现有数据集与实际欺骗策略之间的根本脱节。当前数据集通常通过编辑技术破坏跨模态一致性，导致不真实且易于检测的伪影。相比之下，生成式视频虚假信息力求跨模态的语义一致性以保持真实感。为弥补这一差距，我们引入了RAVM：首个真实感AI生成视频虚假信息检测数据集。与仅限于单一来源操纵的现有视频虚假信息检测（VMD）数据集不同，RAVM涵盖多种操纵来源——声明、视频、音频和跨模态操纵——每种来源结合多种操纵技术以生成真实感AI生成视频虚假信息。为实现这一目标，我们引入了一种智能体驱动的框架来生成真实感视频虚假信息。此外，我们提出了一种IEEG模型，将多模态证据、事实核查结果及其依赖关系表示为证据图，以实现对AI生成视频虚假信息的可解释检测。在RAVM上的大量实验揭示了现有多模态大语言模型（MLLM）在检测AI生成视频虚假信息方面的脆弱性，而所提出的IEEG在RAVM上达到了最优性能。数据集公开可用，地址为：https://gitee.com/VR_NAVE/ravm
英文原文摘要 1580 字符
The rapid evolution of generative AI, including such models as Sora, has intensified the threat of video misinformation. A critical challenge in detecting these AI-generated video misinformation lies in a fundamental disconnect between existing datasets and practical deception tactics. Current datasets often disrupt cross-modal consistency through editing techniques, resulting in unrealistic and easily detectable artifacts. By contrast, generative video misinformation strives for semantic consistency across modalities to remain realism. To address this gap, we introduce RAVM: the first Realistic AI-Generated Video Misinformation Detection Dataset. Unlike existing Video Misinformation Detection (VMD) datasets that are limited to single-source manipulations, RAVM encompasses multiple manipulation sources--Claim, Video, Audio, and Cross-Modal Manipulation--each incorporating diverse manipulation techniques to generate realistic AI-generated video misinformation. To achieve this, we introduce an agent-driven framework for generating realistic video misinformation. Furthermore, we propose an IEEG model that represents multimodal evidence, fact-checking results, and their dependencies as an evidence graph for interpretable detection of AI-generated video misinformation. Extensive experiments on RAVM reveal the vulnerability of existing Multimodal Large Language Models (MLLMs) in detecting AI-generated video misinformation, while the proposed IEEG achieves state-of-the-art performance on RAVM. The dataset is publicly available at: https://gitee.com/VR_NAVE/ravm