通过分析视频帧间差异，提升深度伪造检测精度。
VoD: Learning Volume of Differences for Video-Based Deepfake Detection
- 利用连续帧差分捕捉时空不一致性，构建多轴差异特征。
- 在多个数据集上验证，对已训练数据和新数据均表现优异。
- 适合需要高鲁棒性视频伪造检测的场景，如媒体审核。
深度学习与生成式AI技术的快速发展重塑了数字内容生态，产生了高度逼真的深度伪造视频，严重威胁公众信任与数字媒体真实性。本文提出一种新型深度伪造检测框架——体积差异（Volume of Differences, VoD），通过挖掘连续视频帧间的时空不一致性来提升检测准确性。VoD采用渐进式学习策略，结合连续帧差分（CFD）与分步扩展网络，在多轴维度上捕获差异特征。我们在多个知名深度伪造数据集上进行了内部与跨数据集测试，结果表明，该方法在训练数据上表现卓越，并对未见的新数据具备强适应能力。此外，系统性消融实验分析了片段长度、采样步长与间隔等配置的影响，为框架优化提供重要参考。代码已开源：https://github.com/xuyingzhongguo/VoD。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。