AV-Deepfake1M：一个大规模LLM驱动的音视频Deepfake数据集
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
AI总结：
针对真实视频中音视频篡改片段定位的难题，本研究提出了大规模LLM驱动的AV-Deepfake1M数据集，包含超1M个视频，基准测试表明现有方法性能显著下降，将助力下一代deepfake定位方法的构建。
摘要：
即使对于最先进的方法，检测和定位高度逼真的deepfake音视频内容也极具挑战性。虽然该领域的大多数研究集中在检测高质量的deepfake图像和视频，但很少有工作解决定位嵌入在真实视频中的小片段音视频篡改的问题。在本研究中，我们模拟了此类内容的生成过程，并提出了AV-Deepfake1M数据集。该数据集包含针对超过2K名受试者的内容驱动（i）视频篡改、（ii）音频篡改和（iii）音视频篡改，最终产生超过1M个视频。本文详细描述了所提出的数据生成流程，并对生成数据的质量进行了严格分析。利用最先进的deepfake检测和定位方法对所提出的数据集进行的全面基准测试表明，与以前的数据集相比，性能出现了显著下降。所提出的数据集将在构建下一代deepfake定位方法中发挥至关重要的作用。该数据集和相关代码可在https://github.com/ControlNet/AV-Deepfake1M获取。
英文摘要：
The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) audio-visual manipulations for more than 2K subjects resulting in a total of more than 1M videos. The paper provides a thorough description of the proposed data generation pipeline accompanied by a rigorous analysis of the quality of the generated data. The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets. The proposed dataset will play a vital role in building the next-generation deepfake localization methods. The dataset and associated code are available at https://github.com/ControlNet/AV-Deepfake1M .
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。
