用轻量CNN实现高精度图像生成模型溯源，速度快且适应性强。
Scalable Black-Box Model Attribution for Images
- 基于原始图像块的简单CNN，无需模型内部信息即可溯源
- 在DRAGON数据集上达98.0%准确率，对压缩模糊等干扰鲁棒
- 可无监督复现模型谱系，支持新模型少样本适配
生成模型的快速普及带来了模型溯源问题：仅凭一张图像，能否判断其出自哪个模型？现有方法随生成器复杂度提升而愈发复杂，认为越复杂的模型需越复杂的溯源器。我们证明并非如此。RPA（Raw-Patch Attribution）在最严格的黑盒设置下，使用轻量级CNN实现图像溯源。尽管结构简单，其在25类DRAGON数据集上达到98.0%准确率，在27类OpenFake上达92.9%；具备数据高效性，计算成本与候选模型数量无关；对真实世界常见的压缩、模糊和缩放具有鲁棒性。封闭集训练获得的特征提取器具高度泛化能力：同一表征可无监督恢复模型谱系，识别并分组未见生成器，并通过少量样本实现新模型适配而非重新训练。
原文摘要 · Abstract (English)
The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? Existing methods have grown as elaborate as the generators they target, on the as- sumption that a more sophisticated model demands a more sophisticated attributor. We show it does not. RPA (Raw- Patch Attribution) attributes images in the strictest black- box setting with a lightweight CNN. Despite its simplicity, it attributes more models at higher accuracy than prior work, reaching 98.0% on 25-class DRAGON and 92.9% on 27- class OpenFake; it is data-efficient and runs at a cost inde- pendent of the number of candidate models; and it stays ro- bust to the compression, blur, and resizing images undergo in the wild. Training for closed-set attribution yields a ver- satile feature extractor: the same representation recovers model lineage without supervision, flags and groups unseen generators, and admits new models through few-shot adap- tation rather than retraining.
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。