MadDroid: malicious adware detection in Android using deep learning

Saeed Seraj, Michalis Pavlidis, Marcello Trovati, Nikolaos Polatidis

Research output: Contribution to journalArticle (journal)peer-review

29 Downloads (Pure)

Abstract

The majority of Android smartphone apps are free. When an application is used, advertisements are displayed in order to generate revenue. Adware-related advertising fraud costs billions of dollars each year. Adware is a form of advertising-supported software, that turns into malware when it automatically installs additional malware and adware on an infected device, steals user data, and exposes other vulnerabilities. Better techniques for detecting adware are needed due to the evolution of increasingly sophisticated evasive malware, particularly adware. Even though significant work has been done in the area of malware detection, the adware family has received very little attention. This paper presents a deep learning-based scheme called MadDroid to detect malicious Android adware based on static features. Moreover, this paper delivers a novel dataset that consists of malicious Adware and benign applications and an optimised Convolutional neural network (CNN) for detecting Adware infected by malware based on the permissions of the applications. The results indicate an average classification rate that is higher than previous work for individual adware family classification in terms of well-known evaluation metrics.
Original languageEnglish
Pages (from-to)1-28
Number of pages28
JournalJournal of Cyber Security Technology
Early online date22 Aug 2023
DOIs
Publication statusPublished - 22 Aug 2023

Keywords

  • Android
  • malware detection
  • adware
  • neural networks
  • newdataset

Research Centres

  • Data and Complex Systems Research Centre
  • Data Science STEM Research Centre

Fingerprint

Dive into the research topics of 'MadDroid: malicious adware detection in Android using deep learning'. Together they form a unique fingerprint.

Cite this