Machine learning approach to detect malicious mobile apps

Kazemian, Hassan (2022) Machine learning approach to detect malicious mobile apps. IFIP Advances in Information and Communication Technology, 647. pp. 124-135. ISSN 1868-422X, 1868-4238

Text ML approach to detect malicious mobile apps EANN_AIAI.pdf - Accepted Version Restricted to Repository staff only until 10 June 2024. Download (525kB) | Request a copy

Abstract / Description

Malicious developers are developing unsafe mobile apps which puts users at risk of exposing their personal data in unsafe hands. They are using techniques that change over time and their intention is to bypass the detector systems which are mostly rule- based. This paper avoids the limitations of rule-based systems by building a novel malware detector that can detect malicious apps by making use of machine learning techniques primarily focusing on deep neural networks i.e. deep multi-layer perceptron. These techniques have various properties that can adapt and identify various types of malicious applications. Simulation results on various datasets demonstrate clear superiority of this detector over other approaches, as this approach achieves 99% accuracy. Also, the detector is efficient enough to detect within 100 milliseconds or less due to the intelligent use of autoencoder which reduces the dimensions in the feature.

Item Type:	Article
Additional Information:	IFIP International Conference on Artificial Intelligence Applications and Innovations. AIAI 2022: Artificial Intelligence Applications and Innovations
Uncontrolled Keywords:	Deep neural network, Malicious mobile apps, Android
Subjects:	000 Computer science, information & general works > 020 Library & information sciences 600 Technology 600 Technology > 620 Engineering & allied operations
Department:	School of Computing and Digital Media
Depositing User:	Hassan Kazemian
Date Deposited:	14 Dec 2022 10:44
Last Modified:	14 Dec 2022 10:44
URI:	https://repository.londonmet.ac.uk/id/eprint/8083

Actions (login required)

View Item