一种基于合成图像的无数据FaceSwap检测方法
A Dataless FaceSwap Detection Approach Using Synthetic Images
摘要：
用于创建“Deepfakes”的面部交换技术在过去几年中取得了显着进步，现在使我们能够创建逼真的面部操作。目前用于检测deepfakes的深度学习算法已经显示出有希望的结果，但是，它们需要大量的训练数据，并且正如我们所展示的那样，它们偏向于特定的种族。我们提出了一种deepfake检测方法，通过使用StyleGAN3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表现相当，而且当使用少量真实数据进行微调时，它显示出更好的泛化能力。此外，这也减少了可能具有来自特定种族的稀疏数据的面部图像数据集所产生的偏见。
英文摘要：
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 StyleGAN3. 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.
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。
