通过RAW-RGB对齐实现AI生成图像的零样本检测
Zero-shot Detection of AI-Generated Image via RAW-RGB Alignment
提出基于RAW-RGB对齐痕迹的零样本AI生成图像检测方法，利用真实图像在物理到数字转换过程中的参数相关性作为取证特征，可复用于图像取证和真实性验证任务。
原文依据 we propose a novel forensic feature termed alignment trace, which is constructed by modeling a shared RAW-RGB feature space.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式人工智能（GenAI）的进步日益增加了合成图像识别的复杂性，促使人们提出众多零样本/少样本检测方法来更好地应对未知的GenAI。然而，我们观察到现有检测器经常将经过物理变换（例如打印+扫描）的合成图像误分类为真实图像。这一观察的本质在于：从物理世界重新映射到数字空间的图像是否仍应被归类为“合成”？此外，真实图像和合成图像的定义亟需澄清。我们首先大胆提出，图像的真实性取决于它是否源自物理世界，即有必要验证数字图像与物理世界之间的原始相关性。为此，我们首先分析物理到数字的映射过程：光照信号被相机传感器捕获为RAW数据，然后通过相机内部参数转换为RGB数据。这一过程体现了真实场景固有的独特物理线索。基于此，我们提出了一种新的取证特征，称为对齐痕迹，它通过建模共享的RAW-RGB特征空间来构建。该痕迹捕获了真实图像在物理到数字转换过程中固有的参数相关性，从而间接验证图像的物理起源。实验表明，我们的方法仅使用真实的RAW-RGB数据对即可实现最优的零样本检测。当提供额外的先验知识时，该方法可以轻松微调以获得更好的跨域检测性能。我们希望这项工作为零样本合成检测提供一个新的基线，更重要的是，启发取证社区探索真实图像与合成图像之间的本质区别。
英文原文摘要 1871 字符
Advances in generative AI (GenAI) have increasingly complicated the identification of synthetic images, prompting the proposal of numerous zero-/few-shot detection methods to counter unknown GenAI better. However, we observe that existing detectors often misclassify synthetic images with physical transformations (e.g., print+scan) as real. The essence of this observation lies in: should images remapped from the physical world to digital space still be categorized as "Synthetic"? Furthermore, the definition of what constitutes real and synthetic images urgently needs to be clarified. We first boldly propose that the authenticity of an image depends on whether it originates from the physical world, i.e., it is necessary to verify the original correlation between the digital image and the physical world. To this end, we first analyze the physical-to-digital mapping process: illumination signals are captured by camera sensors as RAW data, which is then converted into RGB data via camera internal parameters. This process embodies unique physical cues inherent to real scenes. Based on this, we propose a novel forensic feature termed alignment trace, which is constructed by modeling a shared RAW-RGB feature space. This trace captures the inherent parameter correlations of real images in the physical-to-digital conversion process, thereby indirectly verifying the physical origin of the image. Experiments demonstrate that our method achieves state-of-the-art zero-shot detection using only real RAW-RGB data pairs. When additional prior knowledge is provided, the method can be easily fine-tuned to achieve better cross-domain detection performance. We hope this work provides a new baseline for zero-shot synthetic detection and, more significantly, inspires the forensics community to explore the essential distinctions between real and synthetic images.