VoD：学习差异体积用于基于视频的深度伪造检测
VoD: Learning Volume of Differences for Video-Based Deepfake Detection
AI总结：
本文提出基于差异体积（VoD）的深度伪造检测框架，利用连续帧差分和逐步扩展网络捕获时空不一致性，在数据集内和跨数据集测试中均表现优异，并通过消融研究优化了框架配置。
摘要：
深度学习与生成式人工智能技术的快速发展深刻改变了数字内容格局，催生出逼真的深度伪造内容，对公众信任和数字媒体完整性构成重大挑战。本文提出一种新颖的深度伪造检测框架——差异体积（Volume of Differences, VoD），旨在通过利用连续视频帧之间的时间与空间不一致性来提升检测精度。VoD采用渐进式学习方法，通过使用连续帧差分（consecutive frame differences, CFD）和具有逐步扩展结构的网络，捕获跨多个轴的差异。我们在多个知名深度伪造数据集上，以数据集内测试和跨数据集测试两种场景评估了所提方法。实验结果表明，VoD在其训练数据上表现优异，并对新颖的未见数据展现出较强的适应能力。此外，全面的消融研究考察了片段长度、采样步数和采样间隔的不同配置，为优化该框架提供了有价值的见解。VoD框架的代码可在 https://github.com/xuyingzhongguo/VoD 获取。
英文摘要：
The rapid development of deep learning and generative AI technologies has profoundly transformed the digital contact landscape, creating realistic Deepfake that poses substantial challenges to public trust and digital media integrity. This paper introduces a novel Deepfake detention framework, Volume of Differences (VoD), designed to enhance detection accuracy by exploiting temporal and spatial inconsistencies between consecutive video frames. VoD employs a progressive learning approach that captures differences across multiple axes through the use of consecutive frame differences (CFD) and a network with stepwise expansions. We evaluate our approach with intra-dataset and cross-dataset testing scenarios on various well-known Deepfake datasets. Our findings demonstrate that VoD excels with the data it has been trained on and shows strong adaptability to novel, unseen data. Additionally, comprehensive ablation studies examine various configurations of segment length, sampling steps, and intervals, offering valuable insights for optimizing the framework. The code for our VoD framework is available at https://github.com/xuyingzhongguo/VoD.
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。
