Sadia Tasnim Dhruba

Semantic Feature Extraction from PE Headers for Malware Classification

A 60-feature taxonomy is presented that matches EMBER’s F1 in a directly compared head-to-head while using 39 × fewer features, a benign-source hold-out rules out a single-source artefact for the dominant feature, and Wilson-95% PPV bounds under deployment priors quantify what practitioners face at sub-1% malware preva...