arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.07369cs.CV

DF26:我们再也无法分辨真假

DF26: We Cannot Tell Fake From Real Anymore

Severyn Shykula, Andrii Yermakov, Ivan Samarskyi, Dmytro Mishkin, Jan Cech, Anastasiia Mishchuk

首次发表
浏览论文内容

中文总结 AI 辅助

DF26基准包含271个真实和2420个AI生成视频,测试显示人类与先进检测器均接近随机猜测,凸显现有评估局限,需关注模型分布偏移鲁棒性。

中文摘要 AI 辅助

我们提出了DF26,这是一个用于检测AI生成视频的新型基准,其中包含由近期文本到视频和图像到视频模型生成的完全合成片段。这些视频捕捉了单人公开演讲场景,涵盖直接面对摄像头的录制、官方声明和演播室访谈——包括271个真实视频和由七个现代视频模型生成的2420个合成视频。在DF26上的研究表明,人类在检测AI生成视频方面的表现,以及最先进的深度伪造检测器,都接近于随机猜测。我们的结果凸显了当前评估协议的局限性,并促使我们需要明确衡量对现代生成模型分布偏移鲁棒性的基准。

英文摘要

We introduce DF26, a novel benchmark for detecting AI-generated videos containing fully synthetic clips produced by recent text-to-video and image-to-video models. The videos capture single-person public-speaking scenarios, spanning direct-to-camera recordings, official statements, and studio interviews - 271 real and 2,420 synthetic videos generated by seven modern video models. The study on DF26 shows that human performance in detecting AI-generated videos, as well as state-of-the-art deepfake detectors, is close to random chance. Our results highlight the limitations of current evaluation protocols and motivate the need for benchmarks that explicitly measure robustness to modern generative model distribution shifts.

发表机构

  • Ukrainian Catholic University(乌克兰天主教大学)
  • Czech Technical University in Prague(布拉格捷克技术大学)
  • Hover Inc.(Hover公司)
  • Institute of Software Systems of the National Academy of Sciences of Ukraine(乌克兰国家科学院软件系统研究所)

机构由 AI 辅助整理,请以论文原文为准。

↑