Eric Wallace

universal-triggers. Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)

interpretability-tutorial-emnlp2020. Materials for the EMNLP 2020 Tutorial on "Interpreting Predictions of NLP Models"

trickme-interface. Code for the 2019 TACL Paper "Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples"

adversarial-mt. Code for "Imitation Attacks and Defenses for Black-box Machine Translations Systems"

data-poisoning. Concealed Data Poisoning Attacks on NLP Models

numeracy. Code for EMNLP 2019 Paper "Do NLP Models Know Numbers? Probing Numeracy in Embeddings.

AK-classifier. Python

hallucinations. Python

lexical-sub. For nicholas

attacking-finetuning-api.