2015
DOI: 10.1049/iet-ifs.2014.0099
|View full text |Cite
|
Sign up to set email alerts
|

High accuracy android malware detection using ensemble learning

Abstract: Abstract-With over 50 billion downloads and more than 1.3 million apps in Google's official market, Android has continued to gain popularity amongst smartphone users worldwide. At the same time there has been a rise in malware targeting the platform, with more recent strains employing highly sophisticated detection avoidance techniques. As traditional signature based methods become less potent in detecting unknown malware, alternatives are needed for timely zero-day discovery. Thus this paper proposes an appro… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
80
0
4

Year Published

2015
2015
2021
2021

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 158 publications
(86 citation statements)
references
References 34 publications
(66 reference statements)
2
80
0
4
Order By: Relevance
“…Researchers built ensemble malware detectors [1,10,11,14,17,18,20,22,24,25,29,30,35,36,38], based on combining general detectors. Moreover, most of them used off-line analysis [1,10,14,25,29,30,35,36]. A few used dynamic analysis [11,20,24] and some used both static and dynamic analysis [17,18,22].…”
Section: Related Workmentioning
confidence: 99%
“…Researchers built ensemble malware detectors [1,10,11,14,17,18,20,22,24,25,29,30,35,36,38], based on combining general detectors. Moreover, most of them used off-line analysis [1,10,14,25,29,30,35,36]. A few used dynamic analysis [11,20,24] and some used both static and dynamic analysis [17,18,22].…”
Section: Related Workmentioning
confidence: 99%
“…(2) Performance comparison: next, we compare the detection performance of Mlifdect with some state-of-theart approaches, including Drebin [3] and emphFest [4], as well as two detection approaches presented by Yerima et al One is based on improved eigenface algorithm [18] and another is based on ensemble learning [6], which we call them Eigenspace and HAEL.…”
Section: Discussionmentioning
confidence: 99%
“…malware. In particularly, we consider Eigenspace [18], HAEL [6], Fest [4], and Drebin [3]. Moreover, we also compare Mlifdect with several single classification algorithms, such as KNN and random forest.…”
Section: Detection With Different Thresholdsmentioning
confidence: 99%
See 1 more Smart Citation
“…Contrary to previous machine learning based dynamic detection work, we attempt to utilize real phones (devices) for automated feature extraction in order to avoid the problem of anti-emulator techniques being employed by Android malware to evade detection. Some previous machine learning based Android malware detection works such as [16], , [33], [13], [32], have considered API calls and Intents in their studies. However, unlike our work, these are based on static feature extraction and thus could be affected by obfuscation.…”
Section: Related Workmentioning
confidence: 99%