Constructing a provably adversarially-robust classifier from a high accuracy one.
Grzegorz GluchRüdiger L. UrbankePublished in: CoRR (2019)
Keyphrases
- high accuracy
- training data
- highly accurate
- decision trees
- high robustness
- class labels
- classification algorithm
- neural network
- feature set
- feature space
- semi supervised
- computationally efficient
- support vector machine svm
- support vector machine
- artificial neural networks
- partial occlusion
- classification scheme
- robust estimation
- classification process
- learning phase
- nearest neighbor classifier
- search algorithm
- robust classification
- label noise