Exposing the Achilles' heel of textual hate speech classifiers using indistinguishable adversarial examples.
Sajal AggarwalDinesh Kumar VishwakarmaPublished in: Expert Syst. Appl. (2024)
Keyphrases
- training examples
- training data
- decision trees
- test set
- data sets
- keywords
- natural language
- training set
- machine learning algorithms
- speech recognition
- lexical features
- dialogue system
- classification models
- svm classifier
- support vector
- ensemble learning
- roc curve
- classification rate
- linear classifiers
- training samples
- majority voting
- hearing impaired