From ae197f8b855569da7c29b85afc12d329e15b4711 Mon Sep 17 00:00:00 2001 From: Fanchao Qi Date: Mon, 27 Jul 2020 23:11:28 +0800 Subject: [PATCH] Update Readme --- README.md | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 90bdc750..65d515c6 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,21 @@

OpenAttack

-![Test](https://github.com/thunlp/OpenAttack/workflows/Test/badge.svg?branch=master) [![Documentation Status](https://readthedocs.org/projects/openattack/badge/?version=latest)](https://openattack.readthedocs.io/en/latest/?badge=latest) ![](https://img.shields.io/badge/PRs-Welcome-red) ![PyPI](https://img.shields.io/pypi/v/OpenAttack?label=OpenAttack) -

- Documentation • Features & Uses • Usage Examples • Attack Models • Toolkit Design + + Github Runner Covergae Status + + + ReadTheDoc Status + + + PyPI version + + + PRs are Welcome +

+ Documentation • Features & Uses • Usage Examples • Attack Models • Toolkit Design +

OpenAttack is an open-source Python-based textual adversarial attack toolkit, which handles the whole process of textual adversarial attacking, including preprocessing text, accessing the victim model, generating adversarial examples and evaluation. @@ -115,11 +126,13 @@ attack_eval.eval(dataset, visualize=True) OpenAttack incorporates many handy components which can be easily assembled into new attack model. -Here gives an example of how to design a simple word swap attack model. +[Here](./examples/custom_attacker.py) gives an example of how to design a simple word swap attack model. #### Advanced: Adversarial Training +OpenAttack can easily generate adversarial examples by attacking instances in the training set, which can be added to original training data set to retrain a more robust victim model, i.e., adversarial training. +[Here](./examples/adversarial_training.py) gives an example of how to conduct adversarial training with OpenAttack. ## Attack Models