固定文本击键动力学中的模板老化与纵向验证：跨越八周的受试者不相交研究
Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks
查看机构详情
- University of Huddersfield（哈德斯菲尔德大学）
- Tianjin University（天津大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究通过八周纵向击键动力学实验，比较四种匹配机制，发现模板老化随间隔单调增加，但机制选择比老化速率更重要，建议基于同会话准确率选匹配器并用重新注册管理老化。
中文摘要 AI 辅助
行为生物特征模板被广泛认为会随着注册与验证之间的间隔增大而退化，但很少有研究在受控条件下直接测量这种模板老化效应。我们收集了一个纵向数据集，包含40个固定密码，在连续八周内每周会话中每个密码输入四次。我们在5折受试者不相交协议下，以及一个同时变化机制和注册到查询间隔（从0到7周）的设计中，比较了缩放曼哈顿匹配器（M1）、梯度提升分类器（M2）、TypeNet风格循环嵌入模型（M3）和TypeFormer风格Transformer（M4）。模板老化被证明是显著且系统性的。对于每种机制，错误随间隔单调增加，从间隔为零时的等错误率14.6%-27.2%增加到七周时的25.5%-37.1%，即每周经过的决策错误增加1.7个百分点（p < 0.001）。然而，机制的选择比其老化速率更重要。四种机制之间的基线准确率跨度达12.6个百分点，而每种机制在七周内累积的退化跨度仅为2.3个百分点，且老化从未重新排序它们。因此，匹配器可以基于同会话准确率进行选择，老化通过重新注册调度来管理，而非通过匹配器选择。然而，这两个属性仍然是不同的，因为M3是最不准确的机制，但在所有测试规格下，其老化速度显著慢于M1。训练随机性也因架构而异，循环模型的折间方差中有58%可归因于种子噪声，而Transformer仅为19%。由于较小的老化率差异对建模选择敏感，而准确率差异和老化效应则不然，我们建议比较性的老化率主张应得到种子级分数融合、独立复制和替代结果模型规格的支持。
英文摘要
Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect directly under controlled conditions. We collected a longitudinal dataset of 40 fixed passwords, each typed four times per weekly session over eight consecutive weeks. We compare a scaled-Manhattan matcher (M1), a gradient-boosted classifier (M2), a TypeNet-style recurrent embedding model (M3), and a TypeFormer-style Transformer (M4) under a 5-fold subject-disjoint protocol and a design that jointly varies mechanism and the enrolment-to-query gap, from 0 to 7 weeks. Template ageing proves large and systematic. Error increases monotonically with the gap for every mechanism, from an EER of 14.6-27.2% at a gap of zero to 25.5-37.1% at seven weeks, or 1.7% of decision error per week elapsed (p < 0.001). However, the choice of mechanism matters more than its rate of ageing. Baseline accuracy spans 12.6 percentage points across the four mechanisms, the degradation each accumulates over seven weeks spans only 2.3 points, and ageing never reorders them. A matcher can therefore be chosen on same-session accuracy, with ageing managed by re-enrolment scheduling rather than by matcher selection. The two properties are nonetheless distinct, as M3 is the least accurate mechanism yet ages significantly more slowly than M1 under every specification tested. Training randomness also matters differently by architecture, with 58% of the recurrent model's fold-to-fold variance attributable to seed noise against 19% for the Transformer. Because the smaller ageing-rate differences are sensitive to modelling choices, while the accuracy differences and the ageing effect are not, we recommend that comparative ageing-rate claims be supported by seed-level score fusion, independent replication, and an alternative outcome-model specification.
