Modern deepfake detectors have achieved encouraging results, when training and test images are drawn from the same data collection. However, when these detectors are applied to images produced with unknown deepfake-generation techniques, considerable performance degradations are commonly observed. In this paper, we propose a novel deepfake detector, called SeeABLE, that formalizes the detection problem as a (one-class) out-of-distribution detection task and generalizes better to unseen deepfakes. Specifically, SeeABLE first generates local image perturbations (referred to as soft-discrepancies) and then pushes the perturbed faces towards predefined prototypes using a novel regression-based bounded contrastive loss. To strengthen the generalization performance of SeeABLE to unknown deepfake types, we generate a rich set of soft discrepancies and train the detector: (i) to localize, which part of the face was modified, and (ii) to identify the alteration type. To demonstrate the capabilities of SeeABLE, we perform rigorous experiments on several widely-used deepfake datasets and show that our model convincingly outperforms competing state-of-the-art detectors, while exhibiting highly encouraging generalization capabilities.

翻译：现代深度伪造检测器在训练与测试图像来自同一数据集合时取得了令人鼓舞的结果。然而，当这些检测器应用于采用未知深度伪造生成技术创作的图像时，通常会出现显著的性能退化。本文提出一种名为SeeABLE的新型深度伪造检测器，该检测器将检测问题形式化为（单类）分布外检测任务，并能更好地泛化至未见过的深度伪造样本。具体而言，SeeABLE首先生成局部图像扰动（称为软差异），随后通过一种新型基于回归的有界对比损失将扰动后的人脸推向预定义原型。为增强SeeABLE对未知深度伪造类型的泛化性能，我们生成丰富的软差异集合并训练检测器：（i）定位人脸中被修改的区域，以及（ii）识别篡改类型。为验证SeeABLE的能力，我们在多个广泛使用的深度伪造数据集上进行了严格实验，结果表明我们的模型在显著优于现有最先进检测器的同时，展现出极具鼓舞性的泛化能力。