As realistic AI-generated images threaten digital authenticity, we address the generalization failure of generative artifact-based detectors by exploiting the intrinsic properties of the camera imaging pipeline. Concretely, we investigate color correlations induced by the color filter array (CFA) and demosaicing, and propose a Demosaicing-guided Color Correlation Training (DCCT) framework for AI-generated image detection. By simulating the CFA sampling pattern, we decompose each color image into a single-channel input (as the condition) and the remaining two channels as the ground-truth targets (for prediction). A self-supervised U-Net is trained to model the conditional distribution of the missing channels from the given one, parameterized via a mixture of logistic functions. Our theoretical analysis reveals that DCCT targets a provable distributional difference in color-correlation features between photographic and AI-generated images. By leveraging these distinct features to construct a binary classifier, DCCT achieves state-of-the-art generalization and robustness, significantly outperforming prior methods across over 20 unseen generators.

翻译：随着逼真的AI生成图像对数字真实性构成威胁，本文通过利用相机成像流程的内在特性，解决了基于生成伪影的检测器泛化失效的问题。具体而言，我们研究了由彩色滤波阵列（CFA）和去马赛克过程诱导的颜色相关性，并提出了一种用于AI生成图像检测的去马赛克引导颜色相关性训练（DCCT）框架。通过模拟CFA采样模式，我们将每个彩色图像分解为单通道输入（作为条件）和剩余两个通道作为真实目标（用于预测）。我们训练一个自监督U-Net模型，以建模从给定通道预测缺失通道的条件分布，该分布通过逻辑函数的混合进行参数化。理论分析表明，DCCT针对摄影图像与AI生成图像之间颜色相关性特征的可证明分布差异进行优化。通过利用这些差异性特征构建二分类器，DCCT实现了最先进的泛化能力和鲁棒性，在超过20种未见过的生成器上显著优于现有方法。