Android Malware Detection: an Eigenspace Analysis Approach

Suleiman Y. Yerima, Sakir Sezer, Igor Muttik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.
LanguageEnglish
Title of host publicationProceedings of the 2015 Science and Information Conference
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1236-1242
Number of pages7
DOIs
Publication statusPublished - 03 Sep 2015
Event2015 SAI Conference - London, United Kingdom
Duration: 28 Jul 201530 Sep 2015

Conference

Conference2015 SAI Conference
CountryUnited Kingdom
CityLondon
Period28/07/201530/09/2015

Fingerprint

Static analysis
Learning systems
Malware

Keywords

  • malware detection
  • machine learning
  • data mining
  • eigenvectors
  • eigenvalue analysis
  • mobile security
  • Android
  • eigenspace
  • static analysis

Cite this

Yerima, S. Y., Sezer, S., & Muttik, I. (2015). Android Malware Detection: an Eigenspace Analysis Approach. In Proceedings of the 2015 Science and Information Conference (pp. 1236-1242). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/SAI.2015.7237302
Yerima, Suleiman Y. ; Sezer, Sakir ; Muttik, Igor. / Android Malware Detection: an Eigenspace Analysis Approach. Proceedings of the 2015 Science and Information Conference . Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 1236-1242
@inproceedings{b0d0cb3017d646909dfa74c9cab5a3cf,
title = "Android Malware Detection: an Eigenspace Analysis Approach",
abstract = "The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96{\%} with a very low false positive rate is achievable using the proposed method.",
keywords = "malware detection, machine learning, data mining, eigenvectors, eigenvalue analysis, mobile security, Android, eigenspace, static analysis",
author = "Yerima, {Suleiman Y.} and Sakir Sezer and Igor Muttik",
year = "2015",
month = "9",
day = "3",
doi = "10.1109/SAI.2015.7237302",
language = "English",
pages = "1236--1242",
booktitle = "Proceedings of the 2015 Science and Information Conference",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

Yerima, SY, Sezer, S & Muttik, I 2015, Android Malware Detection: an Eigenspace Analysis Approach. in Proceedings of the 2015 Science and Information Conference . Institute of Electrical and Electronics Engineers (IEEE), pp. 1236-1242, 2015 SAI Conference, London, United Kingdom, 28/07/2015. https://doi.org/10.1109/SAI.2015.7237302

Android Malware Detection: an Eigenspace Analysis Approach. / Yerima, Suleiman Y.; Sezer, Sakir; Muttik, Igor.

Proceedings of the 2015 Science and Information Conference . Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1236-1242.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Android Malware Detection: an Eigenspace Analysis Approach

AU - Yerima, Suleiman Y.

AU - Sezer, Sakir

AU - Muttik, Igor

PY - 2015/9/3

Y1 - 2015/9/3

N2 - The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.

AB - The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.

KW - malware detection

KW - machine learning

KW - data mining

KW - eigenvectors

KW - eigenvalue analysis

KW - mobile security

KW - Android

KW - eigenspace

KW - static analysis

U2 - 10.1109/SAI.2015.7237302

DO - 10.1109/SAI.2015.7237302

M3 - Conference contribution

SP - 1236

EP - 1242

BT - Proceedings of the 2015 Science and Information Conference

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Yerima SY, Sezer S, Muttik I. Android Malware Detection: an Eigenspace Analysis Approach. In Proceedings of the 2015 Science and Information Conference . Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 1236-1242 https://doi.org/10.1109/SAI.2015.7237302