On CICMalDroid2020, gradient-boosted trees on 564 hybrid features reach about 97.5% accuracy, beating PCA/LDA variants, but the top drivers are spoofable package-name and manifest metadata.
Droiddelver: An android malware detection system using deep belief network based on api call blocks,
1 Pith paper cite this work, alongside 8 external citations. Polarity classification is still indexing.
1
Pith paper citing it
8
external citations · OpenAlex
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Comparison of Multiple Classifiers for Android Malware Detection with Emphasis on Feature Insights Using CICMalDroid 2020 Dataset
On CICMalDroid2020, gradient-boosted trees on 564 hybrid features reach about 97.5% accuracy, beating PCA/LDA variants, but the top drivers are spoofable package-name and manifest metadata.