textfool
textfool copied to clipboard
Plausible looking adversarial examples for text classification
In the data_utils.py, all the token.rank in function extract_features is 0. Hence, X_train and X_test are the same which are the vector as [1, 1, 1, 1....., 0, 0]. What...
Hi! @bogdan-kulynych Thanks for your nice job! I have a puzzle when I run paraphrase.py(not use typos): Original text: **Soft** skills like sharing and negotiating will be crucial. He says...
Hi Guys, When I run the script (run_demo) with the model file generated from the run_training, I get Model accuracy on adversarial examples: 0.6645 Fooling success rate: 0.0 Most of...