LatentForensics：迈向 StyleGAN 潜在空间中的节俭型深度伪造检测
LatentForensics: Towards frugal deepfake detection in the StyleGAN latent space
AI总结：
本文提出 LatentForensics，利用 StyleGAN 潜在空间结构训练轻量级二分类模型进行深度伪造检测，在数据稀缺场景下优于现有方法，为节俭型可解释检测提供新思路。
摘要：
伪造视频的分类在过去几年中一直是一项挑战。深度伪造分类器如今已能可靠地预测视频帧是否被篡改。然而，其性能既受限于训练所用的数据集，也受限于分析人员的计算能力。我们提出一种深度伪造检测方法，该方法在一个基于高质量人脸图像训练的最先进生成对抗网络（GAN）的潜在空间中运行。所提方法利用 StyleGAN 潜在空间的结构来学习一个轻量级二分类模型。在标准数据集上的实验结果表明，所提方法优于其他最先进的深度伪造分类方法，尤其是在可用于训练模型的数据稀缺的情况下，例如当引入一种新的篡改方法时。据我们所知，这是首项表明 StyleGAN 潜在空间对深度伪造分类具有价值的研究。结合近期关于该潜在空间解释与操控的其他研究，我们相信所提方法能够进一步帮助开发基于可解释的高层人脸图像属性的节俭型深度伪造分类方法。
英文摘要：
The classification of forged videos has been a challenge for the past few years. Deepfake classifiers can now reliably predict whether or not video frames have been tampered with. However, their performance is tied to both the dataset used for training and the analyst's computational power. We propose a deepfake detection method that operates in the latent space of a state-of-the-art generative adversarial network (GAN) trained on high-quality face images. The proposed method leverages the structure of the latent space of StyleGAN to learn a lightweight binary classification model. Experimental results on standard datasets reveal that the proposed approach outperforms other state-of-the-art deepfake classification methods, especially in contexts where the data available to train the models is rare, such as when a new manipulation method is introduced. To the best of our knowledge, this is the first study showing the interest of the latent space of StyleGAN for deepfake classification. Combined with other recent studies on the interpretation and manipulation of this latent space, we believe that the proposed approach can further help in developing frugal deepfake classification methods based on interpretable high-level properties of face images.
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。
