Permission-based Android malware detectors exhibit asymmetric domain shift with accuracy dropping from over 92% intra-domain to as low as 73% cross-domain, but hybrid training on common features restores 88-97% accuracy.
PermDroid a framework developed using proposed feature selection approach and machine learning techniques for Android malware detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Diagnosing and Mitigating Domain Shift in Permission-Based Android Malware Detection
Permission-based Android malware detectors exhibit asymmetric domain shift with accuracy dropping from over 92% intra-domain to as low as 73% cross-domain, but hybrid training on common features restores 88-97% accuracy.