Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cybersecurity Attacks and Detection Methods in Web 3.0 Technology: A Review.

Sensors (Basel, Switzerland)·2025
Same author

A Survey on Industrial Internet of Things Security: Requirements, Attacks, AI-Based Solutions, and Edge Computing Opportunities.

Sensors (Basel, Switzerland)·2023
Same author

Intelligent Medical IoT-Enabled Automated Microscopic Image Diagnosis of Acute Blood Cancers.

Sensors (Basel, Switzerland)·2022
Same author

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification.

Sensors (Basel, Switzerland)·2021

Related Experiment Video

Updated: May 17, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K

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

Bandar Alotaibi1, Munif Alotaibi2

  • 1Department of Information Technology, University of Tabuk, Tabuk 47731, Saudi Arabia.

Sensors (Basel, Switzerland)
|May 14, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a hybrid deep learning framework for continuous user authentication on mobile devices using smartphone sensor data. The novel approach achieves high accuracy in identifying users based on their unique motion patterns.

Keywords:
behavioral patternscontinuous user authenticationcybersecuritydeep learningwearable sensors

More Related Videos

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

Related Experiment Videos

Last Updated: May 17, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

Area of Science:

  • Computer Science
  • Cybersecurity
  • Machine Learning

Background:

  • Traditional one-time authentication methods are insufficient for mobile device security.
  • Continuous user authentication is crucial to address evolving mobile security vulnerabilities.

Purpose of the Study:

  • To propose a hybrid deep learning framework for continuous user authentication using smartphone sensor data.
  • To enhance user identification accuracy by integrating computer vision and sequence modeling techniques.

Main Methods:

  • A hybrid deep learning framework combining Vision Transformer (ViT)-inspired patch extraction, multi-head attention, and bidirectional Long Short-Term Memory (BiLSTM) networks.
  • Reshaping raw motion signals into ViT-like patches for short-range pattern capture.
  • Utilizing multi-head attention to highlight discriminative temporal segments and BiLSTM for contextual information integration.

Main Results:

  • The proposed framework achieved high accuracies of 97.51% on the MotionSense dataset and 89.37% on the UCI HAR dataset.
  • Demonstrated superior performance compared to conventional Transformer, Informer, CNN, and LSTM baselines.
  • Effectively extracted local and global motion features specific to individual user behavior.

Conclusions:

  • The hybrid deep learning framework offers a robust solution for continuous user authentication on mobile devices.
  • The method significantly improves user identification accuracy by leveraging unique behavioral motion patterns.
  • This research advances mobile security through innovative deep learning applications.