Abstract :

With The Rapid Growth Of Smartphone Usage, Ensuring Secure And Continuous User Authentication Has Become A Critical Concern. Traditional Authentication Methods Such As Passwords, PINs, And Biometric Verification Provide Only One-time Access Control And Are Vulnerable To Security Threats Such As Theft, Spoofing, And Unauthorized Access. To Overcome These Limitations, This Project Proposes A Non-intrusive Smartphone User Verification System Using Anonymized Multimodal Data. The System Continuously Monitors User Behavior In The Background Without Interrupting The User Experience. The Proposed Approach Utilizes Multiple Data Modalities Such As Touch Patterns, Typing Behavior, Motion Sensors, And Usage Patterns To Uniquely Identify Users. These Behavioral Biometrics Are Collected Anonymously, Ensuring User Privacy And Data Protection. Machine Learning Algorithms Are Employed To Analyze Patterns And Build A User-specific Profile, Enabling Continuous Authentication. The System Detects Deviations From Normal Behavior And Flags Potential Unauthorized Access In Real Time. By Combining Multiple Data Sources, The System Improves Accuracy And Robustness Compared To Single-modal Authentication Methods. Additionally, Anonymization Techniques Ensure That Sensitive User Information Is Not Exposed, Making The System Privacy-preserving. Experimental Results Demonstrate That The Proposed Approach Achieves High Accuracy In Distinguishing Legitimate Users From Intruders. This Solution Provides A Seamless, Secure, And Privacy-aware Authentication Mechanism, Making It Highly Suitable For Modern Smartphone Security Applications.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1920-1927

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite