Enhancing Multifactor Authentication With Machine Learning: A Comprehensive Framework For Robust User Verification

DOI

10.2991/978-94-6463-738-0_52How to use a DOI?

Keywords

Authentication; Accuracy; Biometric; Geolocation; Password

Abstract

This study explores the integration of machine learning techniques with multi-factor authentication (MFA) systems to enhance user verification, security, and usability. Recognizing the vulnerabilities of single-factor authentication methods, we propose an MFA framework combining three distinct verification agents: password authentication, geolocation verification, and biometric authentication. The system leverages covert information-sharing techniques and secure storage mechanisms to ensure robust data protection and user privacy. Continuous authentication experiments conducted on two publicly available datasets demonstrated the effectiveness of machine learning algorithms, with random decision trees achieving accuracy rates exceeding 99% and ensemble learning strategies further enhancing classifier security with an inaccuracy rate of about 5%. The proposed framework achieved 99.46% accuracy for password authentication, 97.37% for geolocation verification, and 100% for biometric authentication. Moreover, the research highlights the balance achieved between stringent security standards and user convenience, with real-time verification approaches ensuring usability without compromising security. Future research will focus on diversifying datasets, optimizing real-time processing capabilities, and incorporating user feedback to enhance system usability and privacy. Investigating user preferences and privacy concerns will be crucial in developing a user-centric MFA solution. Additionally, advanced machine learning models and adaptive authentication strategies will be explored to address emerging threats and increase system resilience. This scalable, adaptable solution provides a robust foundation for developing flexible, secure, and user-friendly authentication frameworks that inspire greater user trust and protection against evolving security challenges.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Imran Qureshi
AU  - Vijay Kale
AU  - Sumegh Tharewal
PY  - 2025
DA  - 2025/06/22
TI  - Enhancing Multifactor Authentication With Machine Learning: A Comprehensive Framework For Robust User Verification
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 646
EP  - 653
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_52
DO  - 10.2991/978-94-6463-738-0_52
ID  - Qureshi2025
ER  -