迈向可持续的通用深度伪造检测：频域遮蔽
Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking
AI总结：
本文提出频域遮蔽方法，用于提升深度伪造检测的泛化能力和计算效率，实现可持续的通用检测。
摘要：
通用深度伪造检测旨在识别跨广泛生成模型（包括未见过的模型）的AI生成图像。这需要具备对新出现的深度伪造内容的鲁棒泛化能力，同时最小化计算开销以实现大规模深度伪造筛查，这在绿色AI时代至关重要。在本文中，我们探索频域遮蔽作为深度伪造检测器的训练策略。与传统方法依赖空间特征或大规模预训练模型不同，我们的方法引入了随机遮蔽和几何变换，重点在于频域遮蔽，因其具有更优异的泛化特性。我们证明频域遮蔽不仅在多样化的生成器上提升了检测准确性，还能在显著模型剪枝下保持性能，提供了一种可扩展且资源节约的解决方案。我们的方法在GAN和扩散生成图像数据集上实现了最先进的泛化能力，并在结构化剪枝下表现出一致的鲁棒性。这些结果突显了基于频域的遮蔽作为实现可持续和可推广深度伪造检测的实用步骤的潜力。代码和模型可在https://github.com/chandlerbing65nm/FakeImageDetection上获得。
英文摘要：
Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and unseen deepfakes, which emerge frequently, while minimizing computational overhead to enable large-scale deepfake screening, a critical objective in the era of Green AI. In this work, we explore frequency-domain masking as a training strategy for deepfake detectors. Unlike traditional methods that rely heavily on spatial features or large-scale pretrained models, our approach introduces random masking and geometric transformations, with a focus on frequency masking due to its superior generalization properties. We demonstrate that frequency masking not only enhances detection accuracy across diverse generators but also maintains performance under significant model pruning, offering a scalable and resource-conscious solution. Our method achieves state-of-the-art generalization on GAN- and diffusion-generated image datasets and exhibits consistent robustness under structured pruning. These results highlight the potential of frequency-based masking as a practical step toward sustainable and generalizable deepfake detection. Code and models are available at https://github.com/chandlerbing65nm/FakeImageDetection.
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。
