Reliable Classification Explanations via Adversarial Attacks on Robust Networks.
Walt WoodsJack ChenChristof TeuscherPublished in: CoRR (2019)
Keyphrases
- machine learning
- feature vectors
- classification accuracy
- pattern recognition
- classification systems
- decision trees
- classification method
- support vector
- automatic classification
- model selection
- complex networks
- support vector machine svm
- pattern classification
- classification models
- classification scheme
- image watermarking
- digital image watermarking
- training samples
- text classification
- machine learning methods
- computer networks
- class labels
- cost sensitive
- training set
- preprocessing
- feature extraction
- feature selection