Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to be overfitted to forgery-specific artifacts, rather than learning features that are widely applicable across various forgeries. To address this issue, we propose a simple yet effective detector called LSDA (\underline{L}atent \underline{S}pace \underline{D}ata \underline{A}ugmentation), which is based on a heuristic idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary, thereby mitigating the overfitting of method-specific features (see Fig.~\ref{fig:toy}). Following this idea, we propose to enlarge the forgery space by constructing and simulating variations within and across forgery features in the latent space. This approach encompasses the acquisition of enriched, domain-specific features and the facilitation of smoother transitions between different forgery types, effectively bridging domain gaps. Our approach culminates in refining a binary classifier that leverages the distilled knowledge from the enhanced features, striving for a generalizable deepfake detector. Comprehensive experiments show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.

翻译：深度伪造检测面临关键泛化难题，当训练数据和测试数据分布不匹配时性能会显著下降。广泛接受的解释是，这些检测器倾向于过拟合伪造特定伪影，而非学习可广泛适用于各类伪造的特征。为解决这一问题，我们提出一种简单而有效的检测器LSDA（潜空间数据增强），其基于启发式思想：包含更丰富伪造类型的表征应能学习到更泛化的决策边界，从而缓解对方法特定特征的过拟合（见图\ref{fig:toy}）。遵循这一思路，我们提出通过构造和模拟潜空间中伪造特征内部及跨特征的变化来扩大伪造空间。该方法涵盖获取丰富的领域特定特征，以及促进不同伪造类型之间的平滑过渡，有效弥合领域鸿沟。最终，我们优化了一个二分类器，利用增强特征中的精炼知识，致力于构建泛化深度伪造检测器。大量实验表明，我们提出的方法效果出奇地好，在多个广泛使用的基准测试中超越了最先进的检测器。