The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the GenImage dataset, we demonstrate that detectors indeed learn from these undesired factors. Furthermore, we show that removing the named biases substantially increases robustness to JPEG compression and significantly alters the cross-generator performance of evaluated detectors. Specifically, it leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors on the GenImage dataset, achieving state-of-the-art results. We provide the dataset and source codes of this paper on the anonymous website: https://www.unbiased-genimage.org

翻译：生成式图像模型的广泛应用凸显了检测人工内容的迫切需求，这是对抗广泛操纵和虚假信息的关键步骤。因此，大量检测器及相关数据集应运而生。然而，这些数据集中的许多无意中引入了不良偏差，从而影响了检测器的有效性和评估。在本文中，我们强调许多用于AI生成图像检测的数据集包含与JPEG压缩和图像尺寸相关的偏差。利用GenImage数据集，我们证明检测器确实会从这些非预期因素中学习。此外，我们表明消除上述偏差能显著增强对JPEG压缩的鲁棒性，并大幅改变评估检测器的跨生成器性能。具体而言，在GenImage数据集上，ResNet50和Swin-T检测器的跨生成器性能提升了超过11个百分点，达到了最新技术水平。我们在匿名网站上提供本文的数据集和源代码：https://www.unbiased-genimage.org