Harnessing Deep Learning for Proactive Detection of Security Threats in Android OS

Murdeshwar, Rajat Nagaraj (2023) Harnessing Deep Learning for Proactive Detection of Security Threats in Android OS. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

In this rapidly evolving domain of mobile technologies, ensuring the security of Android systems is a critical challenge. This research project addresses the urgent need for proactive vulnerability detection in Android OS by developing an automated system that integrates with the National Vulnerability Database (NVD) and Common Weakness Enumeration (CWE). I have designed functions to update its dataset regularly, enabling the immediate detection of newly recorded vulnerabilities. The core of this research project involved the applications of machine learning models and deep learning models: Graph Neural Networks (GNN) using Graph Convolutional Network (GCN), Support Vector Machines (SVM), and Random Forests. These models analyse CVE descriptions, processed through TF-IDF and Word2Vec, to predict vulnerabilities with high accuracy and precision-recall values. The effectiveness of these models demonstrates the project’s contribution to enhancing Android security. Random Forests model with Word2Vec performed well in precision recall with a high accuracy of 98%. A key limitation was the lack of demonstrative code or bad code for all CWE vulnerabilities, restricting the training data’s comprehensiveness.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
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 Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 May 2025 14:14
Last Modified:	18 May 2025 14:14
URI:	https://norma.ncirl.ie/id/eprint/7573

Actions (login required)

View Item