Skip to main content

Table 1 Android malware datasets used by the reviewed papers

From: On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities

Name

Last updated

# APKs

Ground truth

Access

Used by

Android Malware Genome Project (MalGenome) (Zhou and Jiang 2012)

2012

1260 Malware

Provided

Discontinued

Liu and Liu (2014), Arp et al. (2014), Yuan et al. (2016), Zhang et al. (2014), McLaughlin et al. (2017), Demontis et al. (2019), Yerima (2013), Kim et al. (2019), Tong and Yan (2017), Karbab et al. (2018), Aafer et al. (2013), Peiravian and Zhu (2013), Saracino et al. (2018), Amos et al. (2013), Lindorfer et al. (2015), Suarez-Tangil et al. (2017)

DREBIN (Arp et al. 2014)

2014

5560 Malware

Provided

Restricted

Arp et al. (2014), Demontis et al. (2019), Feng et al. (2018), Zhang et al. (2018), Karbab et al. (2018), Suarez-Tangil et al. (2017)

M0Droid (Damshenas et al. 2015)

2015

200 Malware

Provided

Restricted

Milosevic et al. (2017)

Contagio Mobile (Contagio 2021)

2018

~500 Malware

Not Provided

Open

Yuan et al. (2014, 2016),, Wu et al. (2012), Demontis et al. (2019), Saracino et al. (2018), Lindorfer et al. (2015)

VirusShare (2021)

2019

66,727 (Not All Malware)

Not Provided

Restricted

Wang et al. (2014), Kim et al. (2019), Zhu et al. (2018), Xu et al. (2018), Saracino et al. (2018)

AndroZoo (Allix et al. 2016)

2021

15,307,857 (Not All Malware)

Provided

Restricted

Feng et al. (2018)

VirusTotal (2021)

2021

Provided

Paid

Sanz et al. (2013), Lindorfer et al. (2015)

Private sources

N/A

N/A

N/A

Closed

Liu and Liu (2014), Alzaylaee et al. (2020), Zhang et al. (2014), McLaughlin et al. (2017), Wang et al. (2014), Tong and Yan (2017), Feng et al. (2018), Yerima et al. (2014, 2015),, Wu and Hung (2014), Karbab et al. (2018), Burguera et al. (2011)