ANDRUBIS -- 1,000,000 Apps Later: A View on Current Android Malware Behaviors

By Martina Lindorfer, Matthias Neugschwandtner, Lukas Weichselbaum, Yanick Fratantonio, Victor van der Veen, Christian Platzer. 2014

341 citations recorded by the source corpus.

Subfields: Information Systems, 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 Information Systems

1. Battista Biggio
2. Fabio Roli
3. Giorgio Giacinto
4. Davide Maiorca
5. Igino Corona
6. Giorgio Fumera
7. Konrad Rieck
8. Ambra Demontis

In Software

1. Lorenzo Cavallaro
2. Yang Xiang
3. Jun Zhang
4. Giovanni Vigna
5. Surya Nepal
6. Konrad Rieck
7. Daniel Arp
8. Christopher Krügel

In Signal Processing

1. Battista Biggio
2. Giorgio Giacinto
3. Davide Maiorca
4. Fabio Roli
5. Ambra Demontis
6. Konrad Rieck
7. Igino Corona
8. Marco Melis

Citations in the corpus

• Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection (2017, background): “The relevance of this task is witnessed by the fact that Android has become the most popular mobile operating system, with more than a billion users around the world, while the number of malicious applications targeting them has also grown simultaneously: anti-virus vendors detect thousands of new m”
• MalDozer: Automatic framework for android malware detection using deep learning (2018, methodology): “The hybrid analysis methods (Yuan et al., 2014) (Grace et al., 2012) (Bhandari et al., 2015) (Vidas et al., 2014), (Lindorfer et al., 2014) combine between both analyses to improve detection accuracy, which costs additional computational cost.”
• CopperDroid: Automatic Reconstruction of Android Malware Behaviors (2015, background): “Andrubis [28] is an extension to the Anubis dynamic malware analysis system to analyze Android malware [5], [24].”
• Obfuscation-Resilient Privacy Leak Detection for Mobile Apps Through Differential Analysis (2017, background): “Furthermore, static and dynamic analysis approaches for mobile apps usually only inspect data flow in Dalvik bytecode (i.e., the Java component of the app) and miss data leaks in native code components, which are becoming more and more prevalent [5], [26].”
• The Evolution of Android Malware and Android Analysis Techniques (2017, neutral): “Native-based attacks can also be used on at least 30% of the million apps Andrubis analyzed as they were vulnerable to web-based attacks by exposing native Java objects [Lindorfer et al. 2014].”
• A Survey of Android Malware Detection with Deep Neural Models (2020, methodology): “Furthermore, several traditional ML-based Android malware detectors such as TaintDroid [63], Andrubis [64], EnDroid [65], MARVIN [66], and Mobile-sandbox [67] were proposed to utilize the dynamic behavioral features.”
• Deep Ground Truth Analysis of Current Android Malware (2017, methodology): “Veen, V., Platzer, C.: ANDRUBIS - 1,000,000 apps later: a view on current android malware behaviors.”
• AVclass: A Tool for Massive Malware Labeling (2016, methodology): “The Andru-0 bis dataset [17] contains hashes of samples submitted by users to be analyzed by the Andrubis online service.”