NORMA eResearch @NCI Library

BehavioGuard: A Gesture-Based Authentication System for Mobile Applications

Abdur Rahman, Abbas (2024) BehavioGuard: A Gesture-Based Authentication System for Mobile Applications. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (1MB) | Preview

Abstract

The drastic rise in the use of the mobile phones particularly the smart mobile phones has been a wakeup call to come up with warrant security measures to enhance on the protection of data and applications. Password for instance is common modes of authentications that are also steadily being transferred to the absurd by cyber-criminals. To solve such problems, I have designed an AI based system, BehavioGuard for increased security in Android applications for which the envisaged usage is behavioral biometrics for security improvement.

Despite the fact that it goes under the name of BehavioGuard and employs an Android application, biometric parameters such as typing speed, swipe patterns, or motion gestures can be obtained. From here this data is passed to a multi input convolutional neural network which can comfortably identify and validate a user. On the other hand, BehavioGuard is not like the usual type of access control known to be of a traditional type that largely revolves around credentials, in this one on the other hand, new behavior is firstly learnt and security patterns are distributed with the help of acquired knowledge arrived at each interactivity.

Al method brought very good results: In their case, the equations of the BehavioGuard have proved to work with nearly 80% Initial precision in identifying users. Accuracy and Precision increases with the increase of data from different users. Then it jumps up to 90%. This high accuracy does prove the efficiency of the method I have offered to expand the meaning of the mobile device security and privacy. Other factors like the precision of the system, its recall and the false positive all go into the making that the developed system is quite efficient concurrently in the detection of any form of cyber threats and the provision of counter measures.

Therefore, in my study, I score the behavioral biometrics as a positive invention with the prospects of enhancing the mobile security and meeting new threats that targets the user’s personal data. Including information protection, it is a programme that enables maintaining sustainable defence of the processes in the digital space from vandals.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Heffernan, Niall
UNSPECIFIED
Uncontrolled Keywords: Android security; Basic operations; Advanced; Steering; Operation with the application; Stylus operation; writing forces; Forces of the touch screen; Android security; behavioral biometrics; anomaly detection; machine learning; unauthorized access; cybersecurity; typing patterns; touch gestures; navigation sequences
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Q Science > QA Mathematics > Computer software > Mobile Phone Applications
T Technology > T Technology (General) > Information Technology > Computer software > Mobile Phone Applications
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 29 Jul 2025 09:50
Last Modified: 29 Jul 2025 09:50
URI: https://norma.ncirl.ie/id/eprint/8286

Actions (login required)

View Item View Item