SAGA：生成式 AI 视频的来源归因
SAGA: Source Attribution of Generative AI Videos
把「真假二分类」升级为多粒度生成源归因（任务类型/模型版本/团队/具体生成器），并给出 T-Sig 时序注意力可视化来解释不同生成器的可区分性；做深伪检测、生成内容取证或数据溯源的研究者可直接复用其视频 Transformer + 视觉基础模型特征的时空伪影建模与 0.5% 标注的预训练-归因策略。
原文依据 we propose Temporal Attention Signatures (\texttt T-Sig ), a novel interpretability method that visualizes learned temporal differences
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 的普及催生了高度逼真的合成视频，加剧了滥用风险，并使二分类的真/假检测器难以应对。我们提出 SAGA（生成式 AI 视频来源归因），这是首个在大规模场景下应对 AI 生成视频来源归因迫切需求的综合框架。与传统检测不同，SAGA 识别的是所使用的具体生成模型。它独特地提供五个层级的多粒度归因：真实性、生成任务（如 T2V/I2V）、模型版本、开发团队以及精确的生成器，从而提供远为丰富的取证洞见。我们新颖的视频 Transformer 架构利用稳健视觉基础模型的特征，有效捕捉时空伪影。关键的是，我们引入了一种数据高效的「预训练-归因」策略，使 SAGA 仅用每类 0.5% 的来源标注数据即可达到最优归因性能，与全监督性能相当。此外，我们提出时序注意力签名（T-Sig），一种新颖的可解释性方法，可视化学习到的时序差异，首次解释了不同视频生成器为何可被区分。在包括跨域场景的公开数据集上的大量实验表明，SAGA 为合成视频溯源树立了新的基准，为取证与监管应用提供了关键且可解释的洞见。
英文原文摘要 1548 字符
The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce \texttt SAGA (\underline S ource \underline A ttribution of \underline G enerative \underline A I videos), the first comprehensive framework to address the urgent need for AI-generated video source attribution at a large scale. Unlike traditional detection, \texttt SAGA identifies the specific generative model used. It uniquely provides multi-granular attribution across five levels: authenticity, generation task (e.g., T2V/I2V), model version, development team, and the precise generator, offering far richer forensic insights. Our novel video transformer architecture, leveraging features from a robust vision foundation model, effectively captures spatio-temporal artifacts. Critically, we introduce a data-efficient pretrain-and-attribute strategy, enabling \texttt SAGA to achieve state-of-the-art attribution using only 0.5% of source-labeled data per class, matching fully supervised performance. Furthermore, we propose Temporal Attention Signatures (\texttt T-Sig ), a novel interpretability method that visualizes learned temporal differences, offering the first explanation for why different video generators are distinguishable. Extensive experiments on public datasets, including cross-domain scenarios, demonstrate that \texttt SAGA sets a new benchmark for synthetic video provenance, providing crucial, interpretable insights for forensic and regulatory applications.