SWIFT：面向少样本免训练生成视频溯源的滑动窗口重建
SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
提出一种基于视频时序映射的免训练少样本归因方法，利用滑动窗口重建损失差异作为信号，可复用于生成内容溯源与模型指纹识别。
原文依据 we define for the first time the "few-shot training-free generated video attribution" task and propose SWIFT
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期视频生成技术取得了显著进展，因而在多个领域得到广泛应用。然而，人们对生成内容可能被滥用日益担忧。追溯生成视频的来源对于减少潜在滥用和识别责任方变得至关重要。现有的视频溯源方法需要额外操作或训练来源归因模型，这可能降低视频质量或需要大量训练样本。为应对这些挑战，我们首次定义了“少样本免训练生成视频溯源”任务，并提出SWIFT，该方法与视频的时序特性紧密结合。通过利用每个视频块内“像素帧（多）到潜变量帧（一）”的时序映射，SWIFT应用固定长度滑动窗口执行两种不同的重建：正常重建与损坏重建。然后，将两种重建之间的损失变化用作溯源信号。我们对五个最优视频生成模型进行了广泛评估。实验结果表明，仅需20个视频样本，SWIFT在所有模型上平均溯源准确率超过90%，甚至能够对HunyuanVideo、EasyAnimate和Wan2.2实现零样本溯源。我们的源代码可在https://github.com/wangchao0708/SWIFT获取。
英文原文摘要 1438 字符
Recent advancements in video generation technologies have been significant, resulting in their widespread application across multiple domains. However, concerns have been mounting over the potential misuse of generated content. Tracing the origin of generated videos has become crucial to mitigate potential misuse and identify responsible parties. Existing video attribution methods require additional operations or the training of source attribution models, which may degrade video quality or necessitate large amounts of training samples. To address these challenges, we define for the first time the "few-shot training-free generated video attribution" task and propose SWIFT, which is tightly integrated with the temporal characteristics of the video. By leveraging the "Pixel Frames(many) to Latent Frame(one)" temporal mapping within each video chunk, SWIFT applies a fixed-length sliding window to perform two distinct reconstructions: normal and corrupted. The variation in the losses between two reconstructions is then used as an attribution signal. We conducted an extensive evaluation of five state-of-the-art (SOTA) video generation models. Experimental results show that SWIFT achieves over 90% average attribution accuracy with merely 20 video samples across all models and even enables zero-shot attribution for HunyuanVideo, EasyAnimate, and Wan2.2. Our source code is available at https://github.com/wangchao0708/SWIFT.