Comparative Evaluation of Ensemble Learning and Supervised Learning in Android Malwares Using Network-Based Analysis

Ali Feizollah*, Nor Badrul Anuar, Rosli Salleh, Fairuz Amalina

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

With the prevalence of mobile devices, the security threats are growing in number and seriousness. Among the mobile operating systems, Google’s Android has been attacked more than others have. From April 2013 until June 2013, the number of malwares were doubled for the Android. In this paper, we evaluate the mobile malwares detection using the ensemble learning and supervised learning. Furthermore, we compare the two learning approaches based on the experimental results. We compared our experimental results with a similar work. The network traffic generated by mobile malwares are analyzed. We use 600 malware samples from the MalGenome data sample to build the dataset. We use two versions of random forest algorithm as our evaluating algorithm, ensemble learning and supervised learning. The empirical results show that the ensemble learning improves the detection of the Android malwares. The ensemble learning achieved 99.6 % of true positive rate while the supervised learning attained 99.4 %.
Original languageEnglish
Title of host publicationAdvanced Computer And Communication Engineering Technology
Subtitle of host publicationProceedings of the 1st International Conference on Communication and Computer Engineering
EditorsHA Sulaiman, MA Othman, MFI Othman, Y AbdRahim, NC Pee
PublisherSpringer Cham
Pages1025–1035
Number of pages11
ISBN (Electronic)9783319076744
ISBN (Print)9783319076737, 9783319384160
DOIs
Publication statusPublished - 14 Nov 2014
Event2014 International Conference on Communication and Computer Engineering - Kuala Lumpur, Malaysia
Duration: 23 Sept 201425 Sept 2014

Publication series

NameLecture Notes in Electrical Engineering
PublisherSpringer
Volume315
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference2014 International Conference on Communication and Computer Engineering
Abbreviated titleICCCE 2014
Country/TerritoryMalaysia
CityKuala Lumpur
Period23/09/1425/09/14

Keywords

  • Android
  • ensemble learning
  • Malgenome
  • mobile malware
  • network-based analysis
  • supervised learning

Fingerprint

Dive into the research topics of 'Comparative Evaluation of Ensemble Learning and Supervised Learning in Android Malwares Using Network-Based Analysis'. Together they form a unique fingerprint.

Cite this