shahrukhx01/bert-probe

BERT Probe: A python package for probing attention based robustness to character and word based adversarial evaluation. Also, with recipes of implicit and explicit defenses against character-level attacks.

语言：Jupyter Notebook · GitHub 星标：18 · Fork：3

话题：adversarial-attacks · adversarial-examples · adversarial-learning · adversarial-machine-learning · bert · natural-language-processing · pytorch · robustness

在 GitHub 上查看原仓库