发表机构
Arizona State University; Marquette University（亚利桑那州立大学; 马凯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
IDSpace是一种新型文档生成器，通过模型引导的贝叶斯优化等技术生成合成身份文档，可提升数字身份验证系统的评估一致性等指标，还发布了含10种欧洲ID类型的359240份合成文档数据集。
AI 中文摘要
随着服务向线上迁移，银行、贷款机构、政府等信任机构必须对远程用户的身份进行验证。欺诈检测工具已广泛应用，但评估和微调这些工具仍存在困难，因为身份文档具有敏感性，因此数据稀缺。合成数据生成提供了可行路径，且需求明确：我们此前在该领域的工作已被下载超过11000次（来自8个部分的汇总数据）。本文引入IDSpace，在三个方向扩展了该领域的研究：第一，我们提出模型引导的贝叶斯优化，仅使用目标域的少量样本，调整生成参数以最大化视觉相似度和与目标域模型的预测一致性；第二，我们将用户指定的元数据（人口统计信息、欺诈模式、采集设备）与自动调整的控制参数（字体样式、噪声水平、图像质量）解耦，允许用户在无需底层专业知识的情况下配置评估；第三，我们突破模板图像的限制，支持扫描件和移动设备拍摄的文档。实验表明，IDSpace在仅使用少量真实样本的情况下，相较于CycleGAN、扩散修复、无引导优化等基线方法，可将评估一致性提升15-45%，同时将训练准确率提升最高9%，与目标域的SSIM相似度提升10%。我们还发布了一个新数据集，包含359240份高质量合成文档，覆盖10种欧洲身份证件类型。
英文摘要
As services move online, trust institutions such as banks, lenders, and governments must verify the identity of remote users. Fraud detection tools are widely available, but evaluating and fine-tuning them remains difficult because identity documents are sensitive and therefore scarce. Synthetic data generation offers a path forward, and demand is clear: our prior work in this area has been downloaded over $11{,}000$ times (aggregated from eight parts). We introduce IDSpace, extending this line of research in three directions. First, we propose model-guided Bayesian optimization, which tunes generation parameters to maximize both visual similarity and prediction consistency with target-domain models given only a few samples from a target domain. Second, we decouple user-specified metadata (demographics, fraud patterns, capture device) from automatically tuned control parameters (font styles, noise levels, image quality), allowing users to configure evaluations without low-level expertise. Third, we expand beyond template images to support scanned and mobile-captured documents. Experiments show IDSpace improves evaluation consistency by $15-45\%$ over baselines including CycleGAN, diffusion inpainting, and non-guided optimization, using only a few real samples, while improving training accuracy by up to $9\%$ and SSIM similarity with the target domain by $10\%$. We also released a new dataset consisting of $359{,}240$ high-quality synthetic documents across ten European ID types.
