面向通用深度伪造检测的频率掩码
Frequency Masking for Universal Deepfake Detection
AI总结：
本文首次将掩码图像建模引入通用深度伪造检测，提出基于频率掩码的新型检测器，在跨生成方法泛化性能上显著超越现有方法。
摘要：
我们研究通用深度伪造检测。我们的目标是检测来自多种生成式人工智能方法的合成图像，尤其是那些在深度伪造检测器训练期间未曾见过的新兴方法生成的图像。通用深度伪造检测需要出色的泛化能力。受最近提出的掩码图像建模的启发——该方法已在自监督预训练中展现出优异的泛化性能——我们首次尝试探索将掩码图像建模用于通用深度伪造检测。我们研究了训练深度伪造检测器时的空间域和频率域掩码。基于实证分析，我们提出了一种新颖的基于频率掩码的深度伪造检测器。我们对频率域的关注与大多数主要针对空间域检测的方法不同。我们的对比分析表明，与现有方法相比，该方法在性能上取得了显著提升。代码和模型已公开。
英文摘要：
We study universal deepfake detection. Our goal is to detect synthetic images from a range of generative AI approaches, particularly from emerging ones which are unseen during training of the deepfake detector. Universal deepfake detection requires outstanding generalization capability. Motivated by recently proposed masked image modeling which has demonstrated excellent generalization in self-supervised pre-training, we make the first attempt to explore masked image modeling for universal deepfake detection. We study spatial and frequency domain masking in training deepfake detectors. Based on empirical analysis, we propose a novel deepfake detector via frequency masking. Our focus on frequency domain is different from the majority, which primarily target spatial domain detection. Our comparative analyses reveal substantial performance gains over existing methods. Code and models are publicly available.
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。
