测试主流生成模型能否伪造逼真身份证件，发现仅能骗过人眼。
Can Generative Models Actually Forge Realistic Identity Documents?
- 用多款开源扩散模型生成证件照，测试其真实性。
- 生成结果在外观上像，但结构和防伪特征明显不符。
- 适合关注生成内容安全与身份验证的从业者阅读。
生成式图像模型近年来在图像真实感方面取得显著进展，引发公众对其被滥用于文件伪造的担忧。本文探讨当前开源且公开可用的基于扩散的生成模型是否能制作出可真实通过人工或自动化验证系统的身份文件伪造品。我们评估了多种公开生成模型家族（包括Stable Diffusion、Qwen、Flux、Nano-Banana等）的文本到图像及图像到图像生成流程。结果显示，尽管当前生成模型能模拟文档的表面美学特征，却无法再现其结构与法证真实性。因此，生成式身份文件深度伪造达到法证级真实性的风险可能被高估，强调了机器学习从业者与文件法证专家协作进行真实风险评估的重要性。
原文摘要 · Abstract (English)
Generative image models have recently shown significant progress in image realism, leading to public concerns about their potential misuse for document forgery. This paper explores whether contemporary open-source and publicly accessible diffusion-based generative models can produce identity document forgeries that could realistically bypass human or automated verification systems. We evaluate text-to-image and image-to-image generation pipelines using multiple publicly available generative model families, including Stable Diffusion, Qwen, Flux, Nano-Banana, and others. The findings indicate that while current generative models can simulate surface-level document aesthetics, they fail to reproduce structural and forensic authenticity. Consequently, the risk of generative identity document deepfakes achieving forensic-level authenticity may be overestimated, underscoring the value of collaboration between machine learning practitioners and document-forensics experts in realistic risk assessment.
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。