GBU-Palm：用于掌纹呈现攻击检测的多模态视频数据集与基准
GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection
浏览论文内容
中文总结 AI 辅助
本文提出GBU-Palm多模态掌纹PAD数据集与基准，通过控制泄漏协议分离身份与攻击谱系，测试4种视频架构，发现环境变化下架构性能下降，RGB-NIR融合未始终优于仅RGB输入，为跨环境掌纹PAD研究提供基准。
中文摘要 AI 辅助
现有掌纹呈现攻击检测（PAD）数据集常受限于静态图像、采集条件受限或多模态视频数据不足，阻碍了跨环境、模态和攻击类型的系统评估。本文提出GBU-Palm，这是一个大规模多模态视频数据集与基准，包含105名受试者的21326个视频、210个手掌，覆盖6种采集环境，含真实样本、打印攻击和重放攻击，其中有6310个同步RGB-NIR样本。我们构建了控制泄漏的协议，将手掌身份与攻击谱系分离，并在环境匹配和保留环境设置下对4种代表性视频架构进行基准测试。结果显示，环境变化下存在显著的架构相关性能下降，且RGB-NIR融合并不始终优于仅RGB输入。我们进一步通过真实接受（TA）、真实拒绝（TR）、错误接受（FA）、错误拒绝（FR）分解、光谱掩码、时序顺序干预以及冻结骨干网络的NIR探测来分析模型行为，揭示了不同架构的 distinct 失败模式和证据利用情况。GBU-Palm为开发和评估跨环境条件下鲁棒的多模态掌纹PAD方法提供了统一且具有挑战性的基准。
英文摘要
Existing palm presentation attack detection (PAD) datasets are often limited by static imagery, restricted acquisition conditions, or insufficient multimodal video data, hindering systematic evaluation across environments, modalities, and attack types. We present GBU-Palm, a large-scale multimodal video dataset and benchmark containing 21,326 videos from 105 subjects and 210 palms across six acquisition environments, including bona fide, Print, and Replay presentations, with 6,310 synchronized RGB-NIR samples. We construct leakage-controlled protocols that separate palm identity and attack lineage and benchmark four representative video architectures under environment-matched and held-out-environment settings. Results reveal substantial architecture-dependent degradation under environmental shift and show that RGB-NIR fusion does not consistently outperform RGB-only input. We further analyze model behavior through true accept (TA), true reject (TR), false accept (FA), and false reject (FR) decomposition, spectral masking, temporal-order intervention, and frozen-backbone NIR probing, revealing distinct failure patterns and evidence utilization across architectures. GBU-Palm provides a unified and challenging benchmark for developing and evaluating robust multimodal palm PAD methods under cross-environment conditions.
