analiza aiqbench
This arXiv preprint applies deep learning (temporal convolutional networks, contrastive learning, population-based training, and a four-model ensemble) to keystroke-based login and continuous re-authentication. The reported 3.77% EER for fixed-text login is a benchmark result on the GREYC dataset, while free-text performance (10.05% EER) is notably weaker and was measured on the Buffalo dataset. Readers should treat these as single-dataset, unreplicated numbers, and the real-world robustness of "behavioral drift" modeling remains untested.
Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication
arXiv:2610.40398v1 Announce Type: cross Abstract: This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security through continuous behavioral drift monitoring. Level 1 employs fixed-text password authentication using Temporal Convolutional Networks (TCN) with contrastive learning and population-based training (PBT), achieving 3.77% EER for high-security login verification. Upon successful authentication, Level 2 continuously monitors user typing during natural free-text sessions using a 4-Model Deep Learning Ensemble. If suspicious behavioral drift is detected during monitoring, the system re-authenticates the user by returning to Level 1, providing a feedback loop against session hijacking and behavioral anomalies. The system explicitly models long-term behavioral drift through the fixed-text component's PBT mechanism, which adapts to temporal variations in password typing patterns. This research leverages free-text (Buffalo dataset) and fixed-text (GREYC dataset) keystroke dynamics datasets, extracting temporal and spatial features including hold times, up-down latencies, down-down intervals, and trigram patterns. The final system achieves 96%+ accuracy for fixed-text authentication (3.77% EER) and 83.53% True Acceptance Rate (TAR) at 5% False Acceptance Rate (FAR) for free-text continuous authentication (10.05% EER), demonstrating superior performance and strong resistance to impostor attacks through continuous behavioral monitoring.
Abstract:This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security through continuous behavioral drift monitoring. Level 1 employs fixed-text password authentication using Temporal Convolutional Networks (TCN) with contrastive learning and population-based training (PBT), achieving 3.77% EER for high-security login verification. Upon successful authentication, Level 2 continuously monitors user typing during natural free-text sessions using a 4-Model Deep Learning Ensemble. If suspicious behavioral drift is detected during monitoring, the system re-authenticates the user by returning to Level 1, providing a feedback loop against session hijacking and behavioral anomalies. The system explicitly models long-term behavioral drift through the fixed-text component's PBT mechanism, which adapts to temporal variations in password typing patterns. This research leverages free-text (Buffalo dataset) and fixed-text (GREYC dataset) keystroke dynamics datasets, extracting temporal and spatial features including hold times, up-down latencies, down-down intervals, and trigram patterns. The final system achieves 96%+ accuracy for fixed-text authentication (3.77% EER) and 83.53% True Acceptance Rate (TAR) at 5% False Acceptance Rate (FAR) for free-text continuous authentication (10.05% EER), demonstrating superior performance and strong resistance to impostor attacks through continuous behavioral monitoring.
Cryptography and Security (cs.CR); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
arXiv:2610.40398 [cs.CR]
(or arXiv:2610.40398v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2610.40398 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 · 283 cuvinte
Subiecte conexe
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
arXiv · 27 oct. 2026
Continuous Behavioral Authentication via Multi-Expert BERT Log Analysis for Secure Data Sharing
arXiv · 21 aug. 2026
Nonslop: A Gamified Experiment in Human-AI Collaborative Writing
arXiv · 11 iun. 2026
Towards Interpretable Depression Detection: Linking Acoustic Features to DSM-5 Indicators
arXiv · 28 aug. 2026