Combinatorial Boosting of Ensembles of Diversified Classifiers for Defense Against Evasion Attacks.
Rauf IzmailovPeter LinSridhar VenkatesanShridatt SugrimPublished in: MILCOM (2021)
Keyphrases
- ensemble learning
- countermeasures
- ensemble classifier
- decision stumps
- ensemble methods
- multiple classifier systems
- weighted voting
- base classifiers
- rotation forest
- combining classifiers
- randomized trees
- majority voting
- weak learners
- decision trees
- base learners
- defense mechanisms
- weak classifiers
- boosting algorithms
- classifier ensemble
- random forest
- multiple classifiers
- generalization ability
- ddos attacks
- random forests
- intrusion detection
- boosting framework
- diversity measures
- improving classification accuracy
- accurate classifiers
- ensemble members
- classifier combination
- information security
- individual classifiers
- naive bayes
- classification systems
- fusion methods
- machine learning methods
- adaboost algorithm
- imbalanced data
- machine learning
- network security
- classification algorithm
- trained classifiers
- multi class
- feature selection
- negative correlation learning
- decision forest
- bayesian classifiers
- feature ranking
- meta learning
- loss function
- prediction accuracy
- training set
- learning algorithm
- generalization bounds
- fusion method
- combining multiple
- cost sensitive
- machine learning algorithms
- classification accuracy
- boosted classifiers
- support vector