Deepfake Detection through Deep Learning
Deepfake Detection through Deep Learning
复制标题
通过深度学习进行 Deepfake 检测
DOI：
10.1109/bdcat50828.2020.00001
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
R. Sinnott
中科院分区：
文献类型：
--
作者：
Deng Pan;Li Sun;Rui Wang;Xingjian Zhang;R. Sinnott
Deepfake允许自动生成和创建(虚假)视频内容，例如通过生成性对抗网络。深伪技术是一项有争议的技术，有许多影响社会的广泛问题，例如选举偏见。许多研究都致力于开发检测方法，以减少深度假货的潜在负面影响。应用神经网络和深度学习是一种方法。在本文中，我们将深度伪检测技术Xception和MobileNet作为两种自动检测深度伪视频的分类任务的方法。我们使用了来自FaceForensics++的训练和评估数据集，其中包括使用四种不同的流行深度假冒技术生成的四个数据集。结果表明，在所有数据集上都有很高的准确率，准确率在91%-98%之间变化，这取决于所应用的深度假技术。我们还开发了一种投票机制，可以使用所有四种方法的聚合来检测虚假视频，而不是只使用一种方法。
Deepfakes allow for the automatic generation and creation of (fake) video content, e.g. through generative adversarial networks. Deepfake technology is a controversial technology with many wide reaching issues impacting society, e.g. election biasing. Much research has been devoted to developing detection methods to reduce the potential negative impact of deepfakes. Application of neural networks and deep learning is one approach. In this paper, we consider the deepfake detection technologies Xception and MobileNet as two approaches for classification tasks to automatically detect deepfake videos. We utilise training and evaluation datasets from FaceForensics++ comprising four datasets generated using four different and popular deepfake technologies. The results show high accuracy over all datasets with an accuracy varying between 91–98% depending on the deepfake technologies applied. We also developed a voting mechanism that can detect fake videos using the aggregation of all four methods instead of only one.