Generating Natural Language Attacks in a Hard Label Black Box Setting.
Rishabh MaheshwarySaket MaheshwaryVikram PudiPublished in: CoRR (2020)
Keyphrases
- black box
- natural language
- black boxes
- white box
- knowledge representation
- semantic analysis
- rule extraction
- countermeasures
- integration testing
- hybrid systems
- multi label
- natural language processing
- data sets
- watermarking scheme
- database
- information extraction
- active learning
- database systems
- case study
- machine learning