论文标题
面部 - 击打deepfake视频的模型归因
Model Attribution of Face-swap Deepfake Videos
论文作者
论文摘要
AI创建的面部交通视频（通常称为Deepfakes）引起了广泛的关注，作为强大的模仿攻击。现有的关于深击的研究主要集中在二进制检测上，以区分真实视频和虚假视频。但是，确定假视频的特定生成模型也很重要，这可以将其归因于法医调查的来源。在本文中，我们通过研究DeepFake视频的模型归因问题来填补这一空白。我们首先基于几种自动编码器模型引入了一个带有来自不同模型（DFDM）的深击的新数据集。具体而言，使用编码器，解码器，中间层，输入分辨率和压缩比的五个生成模型已被用于基于同一输入的总共6,450个深击视频。然后，我们将DeepFakes模型归因作为多类分类任务，并提出了一种基于空间和时间关注的方法，以探索新数据集中的深击之间的差异。实验评估表明，大多数现有的深层检测方法在DeepFakes模型归因中都失败了，而所提出的方法在高质量的DFDM数据集上获得了超过70％的精度。
AI-created face-swap videos, commonly known as Deepfakes, have attracted wide attention as powerful impersonation attacks. Existing research on Deepfakes mostly focuses on binary detection to distinguish between real and fake videos. However, it is also important to determine the specific generation model for a fake video, which can help attribute it to the source for forensic investigation. In this paper, we fill this gap by studying the model attribution problem of Deepfake videos. We first introduce a new dataset with DeepFakes from Different Models (DFDM) based on several Autoencoder models. Specifically, five generation models with variations in encoder, decoder, intermediate layer, input resolution, and compression ratio have been used to generate a total of 6,450 Deepfake videos based on the same input. Then we take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes in the new dataset. Experimental evaluation shows that most existing Deepfakes detection methods failed in Deepfakes model attribution, while the proposed method achieved over 70% accuracy on the high-quality DFDM dataset.
