Generative AI technologies produce hyper-realistic imagery that can be used for nefarious purposes such as producing misleading or harmful content, among others. This makes Synthetic Image Detection (SID) an essential tool for defending against AI-generated harmful content. Current SID methods typically resize input images to a fixed resolution or perform center-cropping due to computational concerns, leading to challenges in effectively detecting artifacts in high-resolution images. To this end, we propose TextureCrop, a novel image pre-processing technique. By focusing on high-frequency image parts where generation artifacts are prevalent, TextureCrop effectively enhances SID accuracy while maintaining manageable memory requirements. Experimental results demonstrate a consistent improvement in AUC across various detectors by 5.7% compared to center cropping and by 14% compared to resizing, across high-resolution images from the Forensynths and Synthbuster datasets.

翻译：生成式人工智能技术能够生成超逼真的图像，这些图像可能被用于恶意目的，例如制作误导性或有害内容等。这使得合成图像检测成为防御AI生成有害内容的重要工具。当前的合成图像检测方法通常出于计算考虑，将输入图像调整为固定分辨率或进行中心裁剪，这导致在有效检测高分辨率图像中的伪影方面面临挑战。为此，我们提出了TextureCrop，一种新颖的图像预处理技术。通过聚焦于生成伪影普遍存在的高频图像区域，TextureCrop在保持可控内存需求的同时，有效提升了合成图像检测的准确率。实验结果表明，在Forensynths和Synthbuster数据集的高分辨率图像上，相比中心裁剪，该方法使多种检测器的AUC指标平均提升了5.7%；相比直接缩放，平均提升了14%。