发表机构
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（武汉大学计算机学院多媒体软件国家工程研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对深度伪造检测泛化难的问题，提出面向伪影的解缠框架，通过语义对齐的跨生成器重建保留伪影多样性，并引入掩蔽频率感知重建，提升跨数据集和跨生成器的检测性能。
AI 中文摘要
现有的图像伪造检测器通常因捕获可迁移取证线索的能力有限，而难以泛化到未见过的篡改方法。最近的基于跨重建的方法试图通过语义-伪影解缠来提高泛化能力，但通常会将不同生成器产生的异构伪影进行对齐，并在重建过程中排除伪影表示，这可能忽视了篡改伪影固有的多样性和视觉线索。在这项工作中，我们重新审视跨重建，并引入了一个面向伪影的解缠框架，用于鲁棒的图像伪造检测。我们认为，伪影多样性，即不同生成过程引入的篡改伪影的内在变化，包含互补的取证线索，而非不良的域变化。我们的框架不强制显式的伪影对齐，而是通过语义对齐的跨生成器重建来保留多样的伪影特征。此外，我们将伪影表示纳入重建过程，并引入了一种掩蔽的频率感知重建策略，以强调与篡改相关的残差，同时减少语义干扰。这种设计使模型能够从多样的伪影中学习可迁移的取证表示。在多个基准数据集上的大量实验表明，在跨数据集和跨生成器评估设置下均有改进。进一步的分析和消融研究验证了伪影多样性保留和伪影感知跨重建的有效性。
英文摘要
Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable forensic cues. Recent cross-reconstruction based methods attempt to improve generalization through semantic-artifact disentanglement, but typically align heterogeneous artifacts across generators and exclude artifact representations during reconstruction, which may overlook the inherent diversity and visual cues of manipulation artifacts. In this work, we revisit cross-reconstruction and introduce an artifact-oriented disentanglement framework for robust image forgery detection. We argue that \textbf{artifact diversity}, i.e., the intrinsic variations of manipulation artifacts introduced by different generation processes, contains complementary forensic cues rather than undesirable domain variations. Instead of enforcing explicit artifact alignment, our framework preserves diverse artifact characteristics through semantically aligned cross-generator reconstruction. Furthermore, we incorporate artifact representations into the reconstruction process and introduce a masked frequency-aware reconstruction strategy to emphasize manipulation-related residuals while reducing semantic interference. This design enables the model to learn transferable forensic representations from diverse artifacts. Extensive experiments on multiple benchmark datasets demonstrate improvements under both cross-dataset and cross-generator evaluation settings. Further analysis and ablation studies validate the effectiveness of artifact diversity preservation and artifact-aware cross-reconstruction.
