NORMA eResearch @NCI Library

A Lightweight 1-D CNN Model to Detect Android Malware On the Mobile Phone

Parameswaran Lakshmi, Sangameshwaran (2020) A Lightweight 1-D CNN Model to Detect Android Malware On the Mobile Phone. Masters thesis, Dublin, National College of Ireland.

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


The mobile device has become an integrated part of everyone's life. The mobile users store their sensitive and private information in their easy to carry handsets or mobile device (bank information, critical business documents, etc). Android malware is a very big concern for internet security researchers and there have been many research works performed for the detection of android malware on the server-side. The detection of malware on the server-side is not efficient and detection on the mobile device is required to enhance the detection of the loosely controlled android application market. The malware uses obfuscation or repackaging techniques to escape the conservative signature-based analysis. In this paper, a lightweight model using deep neural networks is proposed. The model performs static analysis with help of manifest properties, API calls and application category features. The proposed model leverages the concept of the NLP(Natural Language Processing) to make use of the 1 dimensional convolution neural network (CNN) for malware detection with less training time and pre-processing computational overhead. The lightweight model proposed outperformed commonly used machine learning and deep learning models with an accuracy of 95.50% and this can serve as a great starting point to use the 1-D CNN for effective malware detection on the mobile phone or IoT devices.
Keywords: Android malware, malware detection, deep neural network, 1-dimensional Convolution Neural Network(1D-CNN), Static Analysis, Feature-based, Smartphone Security, API calls, Manifest Properties

Item Type: Thesis (Masters)
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
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Dan English
Date Deposited: 27 Jan 2021 17:35
Last Modified: 27 Jan 2021 17:35

Actions (login required)

View Item View Item