A Dataless FaceSwap Detection Approach Using Synthetic Images
A Dataless FaceSwap Detection Approach Using Synthetic Images
复制标题
DOI：
10.1109/ijcb54206.2022.10007967
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Anubhav Jain;Nasir D. Memon;Julian Togelius
中科院分区：
文献类型：
--
作者：
Anubhav Jain;Nasir D. Memon;Julian Togelius
在过去的几年里，用于创建“Deepfake”的人脸交换技术有了很大的进步，现在我们可以创建逼真的面部操作。目前用于检测深度假冒的深度学习算法已经显示出令人振奋的结果，然而，它们需要大量的训练数据，并且正如我们所表明的那样，它们偏向于特定的种族。我们提出了一种深度伪检测方法，通过使用Style-GAN3合成生成的数据来消除对任何真实数据的需求。这不仅与使用真实数据的传统训练方法不相上下，而且在使用少量真实数据进行微调时显示出更好的泛化能力。此外，这还减少了面部图像数据集造成的偏差，这些数据可能来自特定种族的稀疏数据。为了提高重现性，代码库已公开提供给11https://github.com/anubhav1997/youneednodataset
Face swapping technology used to create “Deepfakes” has advanced significantly over the past few years and now enables us to create realistic facial manipulations. Current deep learning algorithms to detect deepfakes have shown promising results, however, they require large amounts of training data, and as we show they are biased towards a particular ethnicity. We propose a deepfake detection methodology that eliminates the need for any real data by making use of synthetically generated data using Style-GAN3. This not only performs at par with the traditional training methodology of using real data but it shows better generalization capabilities when finetuned with a small amount of real data. Furthermore, this also reduces biases created by facial image datasets that might have sparse data from particular ethnicities. To promote reproducibility the code base has been made publicly available 11https://github.com/anubhav1997/youneednodataset