仅用4张真卡样例，实现跨国家身份卡攻击检测
Towards Zero-Shot Domain Generalization for ID Cards Presentation Attack Detection
- 用原型网络+高效网络骨架，每类仅需4张真卡生成可靠原型
- 在多国数据集上平均错误率9%，优于零样本基线
- 适合需要隐私保护的跨国远程身份验证场景
国家身份证件的呈现攻击检测受限于公开真实样本的缺乏，导致系统难以跨国家泛化。本文提出两项创新：(1) 采用EfficientNet-V2-b0主干网络的原型网络头，每类仅需4张真实样本即可构建可靠原型；(2) 设计一种周期性训练机制，固定攻击类别但轮换证件所属国家，使网络学习通用攻击特征。在大型多国数据集及公开DLC-2021基准上评估，该方法平均等错误率达到约9%，优于传统softmax和CLIP零样本基线，即使仅使用单一来源国家的数据。该方案在保障隐私的同时最小化数据收集，支持可扩展的跨司法管辖区远程开户。
原文摘要 · Abstract (English)
Presentation-Attack Detection (PAD) for national ID cards is limited by the lack of publicly available genuine samples, making it difficult for systems to generalize across countries. This paper introduces two main innovations: (1) a Prototypical Network head using an EfficientNet-V2-b0 backbone that requires only four genuine samples per class to create reliable prototypes; and (2) an episodic training regime that keeps PAD classes fixed while varying the card domain, allowing the network to learn universal attack cues. Evaluated on a large multi-country dataset and the public DLC-2021 benchmark, this method achieves an average Equal Error Rate of around 9\%, outperforming conventional softmax and CLIP zero-shot baselines even with data from a single source country. This approach provides accurate, privacy-preserving PAD while minimizing data collection, facilitating scalable cross-jurisdictional remote onboarding.
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。