/SeqAttack-Visualization

Visualization toolkit for adversarial attacks against token classification models

Primary LanguageVue

attack-viz

Visualize attacks on named entity recognition models. When running click "Open Dataset" and load an attack output file in JSON format. See thesis-code/experiments/... for the files.

A live version is running at https://ner-attack.ashita.nl/

Project setup

npm install

Compiles and hot-reloads for development

npm run serve

Compiles and minifies for production

npm run build

Lints and fixes files

npm run lint

Customize configuration

See Configuration Reference.