通过差异异常检测，识别深层伪造图像中的自然变化异常。
DiffFake: Exposing Deepfakes using Differential Anomaly Detection
- 对比同一人两张脸的嵌入差异，捕捉真实面部变化模式。
- 在五个数据集上表现优于或媲美现有最佳模型。
- 适合应对未知生成技术的深层伪造检测任务。
传统深度伪造检测将问题视为二分类任务，仅在训练中见过特定生成技术时表现良好，但对新方法容易失效。本文提出DiffFake，将检测问题转化为异常检测任务。具体而言，DiffFake利用差分异常检测框架，学习同一人两张人脸图像间的自然变化。通过组合深人脸嵌入对，训练异常检测模型，并进一步在伪深度伪造图像（含全局与局部伪影）上训练特征提取器，以获取可泛化的特征。在五个不同深度伪造数据集上进行大量实验，结果表明该方法性能可匹配甚至超越现有先进模型。
原文摘要 · Abstract (English)
Traditional deepfake detectors have dealt with the detection problem as a binary classification task. This approach can achieve satisfactory results in cases where samples of a given deepfake generation technique have been seen during training, but can easily fail with deepfakes generated by other techniques. In this paper, we propose DiffFake, a novel deepfake detector that approaches the detection problem as an anomaly detection task. Specifically, DiffFake learns natural changes that occur between two facial images of the same person by leveraging a differential anomaly detection framework. This is done by combining pairs of deep face embeddings and using them to train an anomaly detection model. We further propose to train a feature extractor on pseudo-deepfakes with global and local artifacts, to extract meaningful and generalizable features that can then be used to train the anomaly detection model. We perform extensive experiments on five different deepfake datasets and show that our method can match and sometimes even exceed the performance of state-of-the-art competitors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。