AndroZoo: Collecting Millions of Android Apps for the Research Community

By Kevin Allix, Tégawendé F. Bissyandé, Jacques Klein, Yves Le Traon. IEEE Working Conference on Mining Software Repositories, 2016

1,124 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Software, Signal Processing

View Paper: https://www.semanticscholar.org/paper/128add3f0e727b73b3df0ca13b4e818d543bdd98

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

1. Davide Maiorca
2. Giorgio Giacinto
3. Jun Zhang
4. Fabio Martinelli
5. Surya Nepal
6. Mourad Debbabi
7. Corrado Aaron Visaggio
8. Johannes Kinder

In Software

1. Fabio Martinelli
2. Surya Nepal
3. Giorgio Giacinto
4. Xinming Ou
5. Fabio Pierazzi
6. Lorenzo Cavallaro
7. Roberto Jordaney
8. Jacopo Cortellazzi

In Signal Processing

1. Giorgio Giacinto
2. Davide Maiorca
3. Lorenzo Cavallaro
4. Fabio Pierazzi
5. Feargus Pendlebury
6. Fabio Martinelli
7. Wei Luo
8. Surya Nepal

Citations in the corpus

• TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (2018, methodology): “Using Android for our case study simplifies the collection of a large-scale dataset of goodware/malware applications; we evaluate on 129K applications from the AndroZoo [3] dataset1 (with ∼10% malware).”
• Intriguing Properties of Adversarial ML Attacks in the Problem Space (2019, methodology): “We collect apps from AndroZoo [2], a large-scale dataset with timestamped Android apps crawled from different stores, and with VirusTotal summary reports.”
• MalDozer: Automatic framework for android malware detection using deep learning (2018, methodology): “To answer this question, we evaluate MalDozer on four datasets collected from (Allix et al., 2016) of four consecutive years: 2013, 2014, 2015, and 2016, as shown in Table 9, where, we train MalDozer in one year dataset and test it on the rest of the datasets.”
• Amandroid: A Precise and General Inter-component Data Flow Analysis Framework for Security Vetting of Android Apps (2014, methodology): “We evaluated Amandroid on 4,600 real-world apps (2,300 Google Play apps shared by the AndroZoo [3] group, and 2,300 malicious apps from the AMD dataset [50]).”
• On the effectiveness of system API-related information for Android ransomware detection (2018, methodology): “…to two data sources: (i) we crawled the Google Play market using an open-source crawler 7 (ii) we extracted a number of applications from the AndroZoo dataset [2], which features a snapshot of the Google Play store, allowing to access applications without crawling the Google services easily.”
• SourceFinder: Finding Malware Source-Code from Publicly Available Repositories (2020, background): “Second, several efforts maintain databases of malware binaries but without source code [2, 3].”
• A Survey of Android Malware Detection with Deep Neural Models (2020, methodology): “With the support of the customized crawlers like PlayDrone [36], Android apps can be automatically browsed, retrieved, and downloaded into a repository for analysis [37, 38].”
• Deep Ground Truth Analysis of Current Android Malware (2017, background): “AndroZoo ’s goal is to create a comprehensive app collection for software engineering studies.”