DiffFake：利用差分异常检测揭露深度伪造
DiffFake: Exposing Deepfakes using Differential Anomaly Detection
AI总结：
DiffFake将深度伪造检测视为异常检测任务，通过差分框架学习人脸自然变化，并在五个数据集上达到或超越现有方法。
摘要：
传统的深度伪造检测器将检测问题视为二元分类任务。这种方法在训练期间见过给定深度伪造生成技术的样本时能取得令人满意的结果，但面对由其他技术生成的深度伪造时则容易失效。本文提出DiffFake，一种新颖的深度伪造检测器，将检测问题视为异常检测任务。具体而言，DiffFake通过利用差分异常检测框架，学习同一人的两张面部图像之间发生的自然变化。这通过结合成对的深度人脸嵌入，并用它们训练异常检测模型来实现。我们进一步提出在具有全局和局部伪影的伪深度伪造上训练特征提取器，以提取有意义且可泛化的特征，这些特征随后可用于训练异常检测模型。我们在五个不同的深度伪造数据集上进行了广泛实验，结果表明我们的方法能够匹配甚至有时超越最先进竞争者的性能。
英文摘要：
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.
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。
