Adversarial examples causes NLP models to misrecognition.
TextAttack is a Python framework for adversarial attacks, training models in NLP.
# TextFooler textattack attack --model bert-base-uncased-mr --recipe textfooler --num-examples 100 # DeepWordBug textattack attack --model distilbert-base-uncased-cola --recipe deepwordbug --num-examples 100
Last updated 1 year ago