用迁移学习解决跨设备打字认证难题，准确率超现有方法。
Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication
- 通过归纳迁移学习，将主设备打字模式适配到新设备。
- 在BBMAS数据集上实现14.2%等错误率，优于现有方法。
- 适合需要跨设备身份验证的场景，如移动安全登录。
打字动态（按键模式）可作为行为生物特征用于用户认证，例如防止欺诈。尽管该技术在单设备认证中表现良好，但在跨设备场景下更具挑战性：不同设备（如手机与平板）的输入方式差异会导致打字模式变化，引发分布偏移。为此，本文提出一种基于归纳迁移学习的跨设备用户认证系统，将主设备上学习到的打字动态迁移到次设备，并结合少量次设备训练数据，共同训练一个鲁棒的二分类器。同时采用扩展的打字特征集以更精准捕捉区分性动态。在BBMAS数据集上的实验表明，该系统在跨设备场景下达到14.2%的等错误率，优于现有最先进方法。
原文摘要 · Abstract (English)
Keystroke dynamics (typing patterns) can be used as a behavioural biometric modality for user authentication, with applications such as fraud prevention. While the modality has been shown to work well for single device authentication, its application to cross-device scenarios is more challenging. Dynamics learned on one device (eg., phone) may not be directly applicable to authentication on a secondary device with a different form factor (eg., tablet) due to changes in typing patterns that can lead to distribution drifts. To address this, we propose a cross-device user authentication system based on inductive transfer learning, where keystroke dynamics learned on one device are adapted to a secondary device. The adapted data is then combined with necessarily limited training data for the secondary device, which is used to robustly train a binary classifier. Furthermore, an extended set of keystroke features is used to better capture discriminative dynamics. Experiments on the BBMAS dataset show that proposed system achieves an equal error rate of 14.2% for the cross-device scenario, surpassing state-of-the-art methods.
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。