Dissecting Android Malware: Characterization and Evolution

By Yajin Zhou, Xuxian Jiang. 2012

2,325 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Software, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Software

In Signal Processing

Citations in the corpus

Cybersecurity data science: an overview from machine learning perspective (2020, background): “Malware Several malware datasets such as Genome project [73], Virus Share [74], VirusTotal [75], Comodo [76], Contagio [77], DREBIN [78], and Microsoft [79] contain malicious files.”
DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket (2014, methodology): “We run two experiments where we first consider all malware samples of our dataset and then only those samples provided by the Malgenome project [39].”
Semantics-Aware Android Malware Classification Using Weighted Contextual API Dependency Graphs (2014, methodology): “[1] Android Malware Genome Project. http://www.malgenomeproject.org/.”
CHEX: statically vetting Android apps for component hijacking vulnerabilities (2012, background): “Malware are not strangers for both the official Android market and alternative ones [36].”
MADAM: Effective and Efficient Behavior-based Android Malware Detection and Prevention (2018, methodology): “Namely the tested database are the following: Genome : Genome [11] is a collection of 1,242 malicious Android apps collected in 2010 and 2011.”
Malware Detection in Adversarial Settings: Exploiting Feature Evolutions and Confusions in Android Apps (2017, methodology): “Our malware dataset starts with 3,000 malware randomly selected from Genome [44], Contagio [3], VirusShare [4], and Drebin [7].”
Stealth attacks: An extended insight into the obfuscation effects on Android malware (2015, neutral): “The first one is MalGenome [22], a very popular dataset collected by Zhou and Jiang in 2012 [31].”
FeatureSmith: Automatically Engineering Features for Malware Detection by Mining the Security Literature (2016, methodology): “These features may not single out the malicious apps; for example, the SMS sending code is typically invoked from an onClick() method [53], but this method is prevalent across all Android apps.”
The Evolution of Android Malware and Android Analysis Techniques (2017, methodology): “As a result of these downfalls, exempliﬁed by the Google App Veriﬁcation system released in 2012 [Jiang 2012], more effort has been dedicated to implementing semantic signatures, signatures based on functions or methods [Crussell et al. 2012; Zhou et al. 2012].”
Dynodroid: an input generation system for Android apps (2013, background): “We note that many Android malwares are triggered only when specific system events are triggered [29]; Monkey would not be able to expose such malwares.”
A Survey of Deep Learning Methods for Cyber Security (2019, methodology): “[82] 24 Malware Detection Genome Project [67], McAfee Labs”
ANDRUBIS -- 1,000,000 Apps Later: A View on Current Android Malware Behaviors (2014, methodology): “However, the remaining most popular apps (and all other apps submitted 26 times and more) are part of malware corpora, such as Contagio [35] and the Android Malware Genome Project [36].”
Using probabilistic generative models for ranking risks of Android apps (2012, methodology): “We obtained this dataset from the authors of [31].”
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, background): “[98] Genome Project 2012 2689 More than 1,200 malware samples covering the majority of the current Android malware families were collected in this dataset and were systematically characterized from various aspects.”
A Survey of Android Malware Detection with Deep Neural Models (2020, methodology): “The experiments were conducted on 3,000 benign apps from Google Play Store and 8,000 malware from the open-sourced Android Malware Genome Project [109] and VirusShare.”
Checking app behavior against app descriptions (2014, methodology): “For this purpose, we used the dataset of Zhou et al. [28] containing more than 1,200 known malicious apps for Android.”