Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations.
Marek GalovicBranislav BosanskýViliam LisýPublished in: CoRR (2021)
Keyphrases
- training data
- support vector
- classification systems
- automatically generated
- feature selection
- decision trees
- linear classifiers
- reverse engineering
- feature representations
- feature set
- test set
- svm classifier
- malware detection
- ensemble learning
- latent variables
- training set
- classification rate
- training examples
- ensemble classifier
- classifier combination
- neural network