Abstract This study examined the potential use of keystroke dynamics to create keyprints (typing fingerprints) to authenticate individuals in online courses. Previous studies have determined that keystroke typing patterns are unique; in addition to replicating these findings, this study explored best practices for implementing keyprint signatures in situations other than simple password or key phrase verification. While authentication can be difficult when attempting to correctly identify individual users, the results of this study indicate that keyprints can reliably indicate negative cases (a typing sample that is likely not the intended student). The results of this study suggest that complete keyprint signatures are better than keyprint profiles (reduced keyprints based on unique typing patterns only). Results also suggest that keyprint signatures are most reliable when a variety of methods are used to obtain keyprint data (i.e., both copy typing and free typing). Small comparison samples increase the challenge of identification but do not prevent the system from identifying negative cases.

中文翻译：

---

击键动力学：建立密钥表以验证在线课程中的用户

摘要这项研究检查了使用击键动力学创建在线指纹（键入指纹）以验证个人身份的潜在用途。先前的研究已经确定，击键键入模式是唯一的；除了复制这些发现之外，本研究还探讨了在简单密码或关键字验证以外的情况下实施密钥签名的最佳实践。虽然在尝试正确识别单个用户时可能很难进行身份验证，但这项研究的结果表明，键印可以可靠地指示否定情况（打字样本可能不是预期的学生）。这项研究的结果表明，完整的键印签名优于键印配置文件（仅基于唯一的键入模式而减少的键印）。结果还表明，当使用多种方法获取密钥数据时（例如，打字和自由打字），密钥签名最为可靠。较小的比较样本会增加识别的难度，但不会阻止系统识别负面案例。