Ribeiro, José ORCID: https://orcid.org/0000-0002-6526-7334, Saghezchi, Firooz B., Mantas, Georgios ORCID: https://orcid.org/0000-0002-8074-0417, Rodriguez, Jonathan, Shepherd, Simon J. and Abd-Alhameed, Raed A. (2020) An autonomous host-based intrusion detection system for Android mobile devices. Mobile Networks and Applications, 25 (1). pp. 164-172. ISSN 1383-469X (Print), 1572-8153 (Online) (doi:10.1007/s11036-019-01220-y)

Full text not available from this repository. (Request a copy)

Abstract

Intrusion Detection System (IDS) is crucial to protect smartphones from imminent security breaches and ensure user privacy. Android is the most popular mobile Operating System (OS), holding above 85% market share. The traffic generated by smartphones is expected to exceed the one generated by personal computers by 2021. Consequently, this prevalent mobile OS will stay one of the most attractive targets for potential attacks on fifth generation mobile networks (5G). Although Android malware detection has received considerable attention, offered solutions mostly rely on performing resource intensive analysis on a server, assuming a continuous connection between the device and the server, or on employing supervised Machine Learning (ML) algorithms for profiling the malware’s behaviour, which essentially require a training dataset consisting of thousands of examples from both benign and malicious profiles. However, in practice, collecting malicious examples is tedious since it entails infecting the device and collecting thousands of samples in order to characterise the malware’s behaviour and the labelling has to be done manually. In this paper, we propose a novel Host-based IDS (HIDS) incorporating statistical and semi-supervised ML algorithms. The advantage of our proposed IDS is two folds. First, it is wholly autonomous and runs on the mobile device, without needing any connection to a server. Second, it requires only benign examples for tuning, with potentially a few malicious ones. The evaluation results show that the proposed IDS achieves a very promising accuracy of above 0.9983, reaching up to 1.

Item Type:	Article
Uncontrolled Keywords:	Android, intrusion detection system, security, 5G, machine learning, malware detection, host-based IDS, statistical anomaly detection.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Engineering (ENG)
Related URLs:	Publisher Publisher
Last Modified:	18 Aug 2021 10:21
URI:	http://gala.gre.ac.uk/id/eprint/33604

Actions (login required)

View Item