Black-box Smoothing: A Provable Defense for Pretrained Classifiers.
Hadi SalmanMingjie SunGreg YangAshish KapoorJ. Zico KolterPublished in: CoRR (2020)
Keyphrases
- black box
- white box
- black boxes
- training data
- decision trees
- hybrid systems
- machine learning algorithms
- support vector
- state transition
- white box testing
- training set
- intrusion detection
- test cases
- test set
- rule extraction
- neural network
- naive bayes
- artificial intelligence
- integration testing
- svm classifier
- classification algorithm
- network security
- training samples
- feature set
- multi class
- machine learning