构建多模型生成图像数据集，用于评估检测器对未知生成器的泛化能力。
GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
- 用三种不同架构的生成模型合成6万张32×32图像，保持统一生成协议。
- 模型在未见生成器上准确率下降至79-96%，暴露泛化短板。
- 适合研究生成图像检测、域适应与跨生成器泛化问题的研究者。
生成式AI快速发展，但其输出的可靠检测能力滞后，尤其在面对未见过的生成器时表现不佳。我们提出GenSyn10，一个与CIFAR-10对齐的合成图像数据集，包含60,000张图像（10类，32×32，50k/10k划分），由三种架构差异显著的前沿模型生成：FLUX.2-dev（Rectified Flow Transformer）、HunyuanImage-3.0（MoE Transformer）和Qwen-Image-2512（Multimodal Diffusion Transformer）。通过模板化提示引擎生成并下采样以保证一致性。我们评估了17个图像分类模型，采用四阶段协议：真实数据基线、零样本迁移、微调和保留性能。尽管存在领域差距，基于CIFAR-10训练的模型在GenSyn10上实现最高96.86%的零样本准确率，微调后提升至99.88%。在真实/合成二分类中，微调模型在已见生成器上达97–99.9%准确率，但在未见生成器上降至79–96%，凸显其在分布外（OOD）泛化上的持续局限。该结果确立GenSyn10作为超越单生成器场景的可控基准，支持鲁棒性、域适应与跨生成器泛化研究。
原文摘要 · Abstract (English)
The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before. We introduce GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32$\times$32, 50k/10k split) generated using three architecturally diverse state-of-the-art models: FLUX.2-dev (Rectified Flow Transformer), HunyuanImage-3.0 (MoE Transformer), and Qwen-Image-2512 (Multimodal Diffusion Transformer), to advance research in AI-generated image detection. A central challenge in this domain is that detectors perform well on known generators but degrade on unseen ones. GenSyn10 addresses this limitation by curating data from multiple contemporary architectures under a standardized generation protocol, enabling controlled and systematic evaluation of out-of-distribution (OOD) generalization to novel generators. Images are generated using a template-based prompt engine and downsampled to ensure consistency. We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention. Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86\% zero-shot accuracy on GenSyn10, increasing to 99.88\% after fine-tuning. In binary real-vs-synthetic classification, fine-tuned models achieve 97-99.9\% accuracy on seen generators but drop to 79-96\% on images from an unseen generator, highlighting persistent limitations in OOD generalization. These results establish GenSyn10 as a controlled benchmark for studying synthetic image detection beyond single-generator settings, supporting research on robustness, domain adaptation, and cross-generator generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。