Proper Network Interpretability Helps Adversarial Robustness in Classification.
Akhilan BoopathySijia LiuGaoyuan ZhangCynthia LiuPin-Yu ChenShiyu ChangLuca DanielPublished in: CoRR (2020)
Keyphrases
- machine learning
- classification accuracy
- classification method
- support vector machine svm
- classification process
- classification scheme
- network model
- pattern recognition
- support vector
- network management
- support vector machine
- feature set
- peer to peer
- image classification
- benchmark datasets
- class labels
- automatic classification
- network traffic
- data sets
- feature space
- decision trees
- feature extraction
- community structure
- multi agent
- classification algorithm
- text classification
- wireless sensor networks
- feature vectors