How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks.
Salijona DyrmishiSalah GhamiziMaxime CordyPublished in: CoRR (2023)
Keyphrases
- multi agent
- word pairs
- sentence level
- text corpus
- text input
- string matching
- keywords
- text segments
- natural language text
- countermeasures
- linguistic information
- related words
- lexical features
- natural language generation
- semantic information
- co occurrence
- word level
- handwritten documents
- text mining
- information retrieval
- syntactic categories