<ul><li>This study addresses the issue of class imbalance in malware detection on mobile devices.</li><li>The study evaluates various machine learning strategies for detecting malware in Android applications.</li><li>The proposed approach focuses on dynamic classifier selection algorithms, which have shown superior performance.</li><li>The empirical analysis demonstrates the effectiveness of the KNOP algorithm using a pool of Random Forest.</li></ul>

Imbalanced malware classification: an approach based on dynamic classifier selection

Discover more