LAVID：一种用于扩散生成视频检测的智能体式LVLM框架
REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection
AI总结：
针对AI生成视频检测研究空白，提出无需训练的智能体式LVLM框架LAVID，通过调用显式知识工具、自改写结构化提示词实现检测，构建新基准VIDFOR，实验显示F1分数较基线提升6.2%至30.2%。
摘要：
生成模型在创建高质量视频方面取得的显著成果，引发了人们对数字完整性与隐私漏洞的担忧。目前AI生成内容检测的相关研究已在图像领域（如深度伪造deepfake）得到广泛探讨，但视频领域仍未被充分探索。大视觉语言模型（Large Vision Language Model，LVLM）凭借强大的推理能力与多模态能力，已成为AI生成内容检测的新兴工具，打破了传统深度学习方法存在的透明度不足、无法识别新型伪影等局限。受此启发，我们提出LAVID，这是一种具备显式知识增强的、基于LVLM的新型AI生成视频检测框架。我们的核心思路如下：（1）主流LVLM可以调用外部工具提取有用信息，辅助自身完成视频检测任务；（2）对提示词进行结构化设计能够影响LVLM解读视频内容信息的推理能力。我们提出的流水线会自动选择一组显式知识工具用于检测，随后通过自改写自适应调整结构化提示词。与现有最优方法（SOTA）需要训练额外检测器不同，我们的方法完全无需训练，仅需对LVLM进行推理即可完成检测。为推动相关研究，我们还构建了一个新基准\textit{VIDFOR}，其中包含由多种视频生成工具生成的高质量视频。评估结果显示，在我们的数据集上，针对四款SOTA级别的LVLM，LAVID的F1分数相比顶级基线模型提升了6.2%至30.2%。
英文摘要：
The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on specific datasets, struggle with the ever-evolving landscape of generative techniques and unseen manipulations. We introduce a framework leveraging Vision Language Models (VLMs) for robust AI-generated video detection. Our approach equips the VLM with the ability to reason about video content and use external tools to identify subtle inconsistencies, mirroring human system 2 thinking. Our self-evolving VLM dynamically selects and composes appropriate tools, enhancing its ability to generalize to novel video generation techniques. The modular design promotes interpretability, allowing for a clearer understanding of VLM's decision-making process. To evaluate, we establish the first benchmark VidForensic containing 1.4k+ high-quality AI-generated videos across eight generative models. Experiments show that REVEAL improves F1 scores by 9.1% to 30.2% over top baselines across our datasets for VLMs, notably for GPT-4o, Gemini 1.5 pro, and QWen-VL-Max, and Llava-One-Vision-7B. While open-world AI-video detection remains an open challenge, our results indicate that existing methods fail primarily because they lack tool-enabled, higher-order reasoning.
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。
