On the impact of dataset size and class imbalance in evaluating machine-learning-based windows malware detection techniques.
Dávid IllésPublished in: CoRR (2022)
Keyphrases
- class imbalance
- malware detection
- machine learning
- active learning
- cost sensitive learning
- class distribution
- feature selection
- cost sensitive
- malicious executables
- anomaly detection
- imbalanced datasets
- pattern recognition
- data mining
- benchmark datasets
- machine learning methods
- concept drift
- learning algorithm
- sampling methods
- minority class
- api calls
- high dimensionality
- machine learning algorithms
- text mining
- unsupervised learning
- application programming interface
- imbalanced class distribution
- reinforcement learning