androidtvmalwaredataset
A dataset of 1000 features extracted from benign and malicious Android TV applications
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
✓Academic publication links
Links to: mdpi.com -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.9%) to scientific vocabulary
Repository
A dataset of 1000 features extracted from benign and malicious Android TV applications
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
AndroidTVMalwareDataset
We are happy to share our malware dataset containing 1000 features extracted from benign and malicious Android TV applications.
If your papers use this dataset, please cite our paper:
Ozogur G, Gurkas-Aydin Z, Erturk MA. Is Malware Detection Needed for Android TV? Applied Sciences. 2025; 15(5):2802. https://doi.org/10.3390/app15052802
```bibtex @Article{app15052802, AUTHOR = {Ozogur, Gokhan and Gurkas-Aydin, Zeynep and Erturk, Mehmet Ali}, TITLE = {Is Malware Detection Needed for Android TV?}, JOURNAL = {Applied Sciences}, VOLUME = {15}, YEAR = {2025}, NUMBER = {5}, ARTICLE-NUMBER = {2802}, URL = {https://www.mdpi.com/2076-3417/15/5/2802}, ISSN = {2076-3417}, ABSTRACT = {The smart TV ecosystem is rapidly expanding, allowing developers to publish their applications on TV markets to provide a wide array of services to TV users. However, this open nature can lead to significant cybersecurity concerns by bringing unauthorized access to home networks or leaking sensitive information. In this study, we focus on the security of Android TVs by developing a lightweight malware detection model specifically for these devices. We collected various Android TV applications from different markets and injected malicious payloads into benign applications to create Android TV malware, which is challenging to find on the market. We proposed a machine learning approach to detecting malware and evaluated our model. We compared the performance of nine classifiers and optimized the hyperparameters. Our findings indicated that the model performed well in rare malware cases on Android TVs. The most successful model classified malware with an F1-Score of 0.9789 in 0.1346 milliseconds per application.}, DOI = {10.3390/app15052802} }
Owner
- Login: gozogur
- Kind: user
- Repositories: 1
- Profile: https://github.com/gozogur
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this dataset, please cite it as below."
title: "AndroidTVMalwareDataset"
authors:
- family-names: "Ozogur"
given-names: "Gokhan"
orcid: "https://orcid.org/0000-0002-8280-5368"
- family-names: "Gurkas-Aydin"
given-names: "Zeynep"
orcid: "https://orcid.org/0000-0002-4125-0589"
- family-names: "Erturk"
given-names: "Mehmet Ali"
orcid: "https://orcid.org/0000-0002-4030-1110"
version: "1.0"
type: dataset
date-released: "2024-03-06"
url: "https://github.com/gozogur/AndroidTVMalwareDataset"
preferred-citation:
type: article
title: "Is Malware Detection Needed for Android TV?"
authors:
- family-names: "Ozogur"
given-names: "Gokhan"
- family-names: "Gurkas-Aydin"
given-names: "Zeynep"
- family-names: "Erturk"
given-names: "Mehmet Ali"
journal: "Applied Sciences"
volume: "15"
issue: "5"
article-number: "2802"
year: "2025"
doi: "10.3390/app15052802"
url: "https://www.mdpi.com/2076-3417/15/5/2802"
keywords:
- "Android TV"
- "Malware Detection"
- "Cybersecurity"
abstract: |
The smart TV ecosystem is rapidly expanding, allowing developers to publish their applications on TV markets to provide a wide array of services to TV users. However, this open nature can lead to significant cybersecurity concerns by bringing unauthorized access to home networks or leaking sensitive information. In this study, we focus on the security of Android TVs by developing a lightweight malware detection model specifically for these devices. We collected various Android TV applications from different markets and injected malicious payloads into benign applications to create Android TV malware, which is challenging to find on the market. We proposed a machine learning approach to detecting malware and evaluated our model. We compared the performance of nine classifiers and optimized the hyperparameters. Our findings indicated that the model performed well in rare malware cases on Android TVs. The most successful model classified malware with an F1-Score of 0.9789 in 0.1346 milliseconds per application.
GitHub Events
Total
- Watch event: 1
- Push event: 1
Last Year
- Watch event: 1
- Push event: 1