EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Deep Learning Framework for Continuous User Authentication Based on Smartphone Sensors

Bandar Alotaibi iD, Munif Alotaibi iD

Sensors · 30.04.2025 · 25 (9) · 2817

DOI: 10.3390/s25092817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.04.2025. Verfasst von Bandar Alotaibi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, University of Tabuk, Tabuk 47731, Saudi Arabia. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Continuous user authentication is critical to mobile device security, addressing vulnerabilities associated with traditional one-time authentication methods. This research proposes a hybrid deep learning framework that combines techniques from computer vision and sequence modeling, namely, ViT-inspired patch extraction, multi-head attention, and BiLSTM networks, to authenticate users continuously from smartphone sensor data. Unlike many existing approaches that directly apply these techniques for specific recognition tasks, our method reshapes raw motion signals into ViT-like patches to capture short-range patterns, employs multi-head attention to emphasize the most discriminative temporal segments, and then processes these enhanced embeddings through a bidirectional LSTM to integrate broader contextual information. This integrated pipeline effectively extracts local and global motion features specific to each user’s unique behavior, improving accuracy over conventional Transformer, Informer, CNN, and LSTM baselines. Experiments on the MotionSense and UCI HAR datasets show accuracies of 97.51% and 89.37%, respectively, indicating strong user-identification performance.

Schlagwörter

Stichwörter der Autor:innen

behavioral patternscontinuous user authenticationcybersecuritydeep learningwearable sensors

Autor:innen und Institutionen

  • Department of Information Technology, University of Tabuk, Tabuk 47731, Saudi Arabia.
  • Dahaa Research Group, Department of Computer Science, Shaqra University, Shaqra 11961, Saudi Arabia.

ORCID-Profile: Bandar Alotaibi, Munif Alotaibi

Zitieren

APA

Alotaibi, B., & Alotaibi, M. (2025). Hybrid Deep Learning Framework for Continuous User Authentication Based on Smartphone Sensors. Sensors, 25(9), 2817. https://doi.org/10.3390/s25092817

Vancouver

Alotaibi B, Alotaibi M. Hybrid Deep Learning Framework for Continuous User Authentication Based on Smartphone Sensors. Sensors. 2025;25(9):2817. doi:10.3390/s25092817

BibTeX
@article{Alotaibi2025,
  author = {Alotaibi, Bandar and Alotaibi, Munif},
  title = {Hybrid Deep Learning Framework for Continuous User Authentication Based on Smartphone Sensors},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2817},
  doi = {10.3390/s25092817}
}
Kostenlos starten →