A pseudo-labeling method with class-specific adaptive thresholds, label-consistent augmentation, and mixup reduces concept-drift performance loss in malware classifiers across five datasets.
Revisit- ing static feature-based 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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
A pseudo-labeling method with class-specific adaptive thresholds, label-consistent augmentation, and mixup reduces concept-drift performance loss in malware classifiers across five datasets.