Individualized Deepfake Detection Dataset

The Deepfake face detection task involves a facial image of unknown authenticity for testing. While most deepfake detection methods take only the image as input, our literature demonstrates that conditioning the deepfake detector on identity—i.e., knowing whose deepfake face the picture might be—can enhance detection performance. Existing deepfake detection datasets, such as FaceForensics++ and DFDC, do not include identity information for authentic and deepfake faces. This dataset contains facial images of 45 specific individuals, divided into train and test sets, including a total of 23k authentic and 22k deepfake images. Having a specific individual's images in both the train and test sets allows us to assess detection performance for that individual. The dataset is curated so that the train and test sets are from two independent sources. The train images are curated from the CelebDFv2 dataset, and the test images are curated from the CACD dataset. Deepfake faces are generated using FaceswapGAN, utilizing a portion of the train images to train the reconstruction model. The test deepfake images are faceswapped with another identity not included in our celebrity list. On the other hand, the train deepfake images are reconstructed images of that person. The deepfake detection method proposed in our paper requires reconstructing both the train and test images. The reconstructed test images and reconstructed train images are also available in this dataset. It is worth mentioning that reconstructing the training deepfake images produces doubly reconstructed images.

深度伪造人脸检测（Deepfake face detection）任务以真实性未知的人脸图像作为测试样本。尽管多数深度伪造检测方法仅以单张图像作为输入，但本研究表明，将检测器基于身份信息进行条件约束（即明确该人脸图像对应的个体身份），可有效提升检测性能。现有深度伪造检测数据集（如FaceForensics++与DFDC）均未提供真实人脸与深度伪造人脸的身份信息。本数据集包含45位特定个体的人脸图像，划分为训练集与测试集，总计包含2.3万张真实人脸图像与2.2万张深度伪造人脸图像。训练集与测试集均覆盖同一特定个体的图像，可用于评估检测器针对该个体的检测性能。本数据集的训练集与测试集分别取自两个独立数据源，以保证数据分布的独立性。训练集真实人脸图像源自CelebDFv2数据集，测试集真实人脸图像源自CACD数据集。深度伪造人脸通过FaceswapGAN生成：使用部分训练集真实图像训练重建模型，进而生成对应个体的深度伪造人脸。测试集深度伪造人脸通过将目标人脸与本数据集名人列表外的另一身份进行人脸交换生成；而训练集深度伪造人脸则为该个体自身的重建图像。本文提出的深度伪造检测方法需要对训练集与测试集图像均进行重建操作，本数据集同时提供了重建后的训练集图像与重建后的测试集图像。值得注意的是，对训练集深度伪造图像进行重建后，将得到二次重建图像。

搜集汇总

背景与挑战

背景概述

该数据集是一个专注于个体化深度伪造检测的数据集，包含45个特定个体的面部图像，总计约23k真实图像和22k深度伪造图像，分为训练集和测试集。其关键特点是强调身份信息对检测性能的提升，训练集来自CelebDFv2，测试集来自CACD，确保来源独立，并提供了用于双神经网络方法的重建图像，支持先进的检测算法研究。