EUVIMEDEUVIMED entdecken
Crossref

CRAFTAuth: Contextual Reconstruction and Adaptive Fusion Transformer for Sensor-Based Continuous Authentication

Yantao Li, Cheng Yu, Hongyu Huang, Huafeng Qin, Shaojiang Deng

IEEE Internet of Things Journal · 2026-08 · 13 (16) · 37779-37793

DOI: 10.1109/jiot.2026.3701766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-08. Verfasst von Yantao Li und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chongqing Municipal Education Commission, Chongqing Municipal Science and Technology Bureau.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, sensor-based continuous authentication on mobile devices has emerged as a promising solution for enhancing personal information security. However, many existing approaches depend on both legitimate and illegitimate user data for supervised training, which is time-consuming and often impractical in real-world deployments. To address these limitations, we propose CRAFTAuth, a sensor-based continuous authentication system built upon context reconstruction and an adaptive fusion transformer. CRAFTAuth leverages built-in smartphone sensors of the accelerometer and gyroscope to capture behavioral biometrics in a nonintrusive manner. The system employs a self-supervised Transformer-based autoencoder to reconstruct long-term behavioral contexts from historical data, enabling the extraction of stable and discriminative features. To enhance adaptability, an iterative attention adaptive fusion (IAAF) mechanism dynamically integrates real-time behavioral inputs with long-term contextual features through progressive spatial–temporal refinement. In addition, a channel merging strategy is incorporated to compress feature representations and reduce computational complexity while preserving temporal dependencies, facilitating efficient deployment on resource-constrained mobile devices. Extensive experiments on our dataset demonstrate that CRAFTAuth achieves state-of-the-art performance, attaining 99.28% accuracy and 0.79% equal error rate (EER), while significantly reducing model size and inference latency compared with existing methods.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Municipal Education Commission
  • Chongqing Municipal Science and Technology Bureau

Zitieren

APA

Li, Y., Yu, C., Huang, H., Qin, H., & Deng, S. (2026). CRAFTAuth: Contextual Reconstruction and Adaptive Fusion Transformer for Sensor-Based Continuous Authentication. IEEE Internet of Things Journal, 13(16), 37779-37793. https://doi.org/10.1109/jiot.2026.3701766

Vancouver

Li Y, Yu C, Huang H, Qin H, Deng S. CRAFTAuth: Contextual Reconstruction and Adaptive Fusion Transformer for Sensor-Based Continuous Authentication. IEEE Internet of Things Journal. 2026;13(16):37779-37793. doi:10.1109/jiot.2026.3701766

BibTeX
@article{Li2026,
  author = {Li, Yantao and Yu, Cheng and Huang, Hongyu and Qin, Huafeng and Deng, Shaojiang},
  title = {CRAFTAuth: Contextual Reconstruction and Adaptive Fusion Transformer for Sensor-Based Continuous Authentication},
  journal = {IEEE Internet of Things Journal},
  year = {2026},
  volume = {13},
  number = {16},
  pages = {37779--37793},
  doi = {10.1109/jiot.2026.3701766}
}
Kostenlos starten →