Android Malware Detection: an Eigenspace Analysis Approach

Suleiman Y. Yerima; Sakir Sezer; Igor Muttik

doi:10.1109/SAI.2015.7237302

Android Malware Detection: an Eigenspace Analysis Approach

Suleiman Y. Yerima, Sakir Sezer, Igor Muttik

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

17 Citations (Scopus)

270 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 2015 Science and Information Conference
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1236-1242
Number of pages	7
DOIs	https://doi.org/10.1109/SAI.2015.7237302
Publication status	Published - 03 Sep 2015
Event	2015 SAI Conference - London, United Kingdom Duration: 28 Jul 2015 → 30 Sep 2015

Conference

Conference	2015 SAI Conference
Country/Territory	United Kingdom
City	London
Period	28/07/2015 → 30/09/2015

Keywords

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

Access to Document

10.1109/SAI.2015.7237302

Android Malware Detection: an Eigenspace Analysis Approach
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Accepted author manuscript, 940 KBLicence: Unspecified

1 Active

R1518ECI: CSIT 2 - EPSRC / TSB
O'Neill, M., Bustard, J., Cao, X., Farshim, P., Kurugollu, F., Liu, W., McCanny, J. V., McLaughlin, K., Miller, P., O'Kane, P., O'Sullivan, E. & Sezer, S.
23/03/2015 → …
Project: Research

Cite this

@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 = sep,

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)",

note = "2015 SAI Conference ; Conference date: 28-07-2015 Through 30-09-2015",

}

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)

T2 - 2015 SAI Conference

Y2 - 28 July 2015 through 30 September 2015

ER -

Android Malware Detection: an Eigenspace Analysis Approach

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

R1518ECI: CSIT 2 - EPSRC / TSB

Cite this