analiza aiqbench
This research addresses the critical challenge of distribution drift in behavioral biometrics by applying transfer learning to enable seamless user authentication across different device form factors. By adapting models from a primary device (e.g., phone) to a secondary one with limited data, the proposed system achieves an equal error rate of 14.2%, outperforming existing state-of-the-art methods for cross-device scenarios. The study highlights how advanced machine learning techniques can enhance fraud prevention and security continuity in heterogeneous mobile ecosystems without requiring extensive retraining on new hardware.
Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication
arXiv:2608.16334v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)
K.6.5; I.2.6; I.5.4
arXiv:2608.16334 [cs.LG]
(or arXiv:2608.16334v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.16334 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 268 cuvinte
