https://github.com/thunlp/sememepso-attack

Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"
https://github.com/thunlp/sememepso-attack

adversarial-attacks adversarial-examples nlp pso sememe

Last synced: 4 days ago
JSON representation

Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"

• Host: GitHub
• URL: https://github.com/thunlp/sememepso-attack
• Owner: thunlp
• License: mit
• Created: 2020-04-28T14:28:38.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-04-11T10:55:12.000Z (over 3 years ago)
• Last Synced: 2024-04-20T13:04:21.910Z (7 months ago)
• Topics: adversarial-attacks, adversarial-examples, nlp, pso, sememe
• Language: Python
• Size: 58.7 MB
• Stars: 85
• Watchers: 9
• Forks: 14
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# SememePSO-Attack

Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization". [[paper]](https://arxiv.org/pdf/1910.12196.pdf)

## Citation

Please cite our paper if you find it helpful.

```

@inproceedings{zang2020word,

  title={Word-level Textual Adversarial Attacking as Combinatorial Optimization},

  author={Zang, Yuan and Qi, Fanchao and Yang, Chenghao and Liu, Zhiyuan and Zhang, Meng and Liu, Qun and Sun, Maosong},

  booktitle={Proceedings of ACL},

  year={2020}

}

```

This repository is mainly contributed by Yuan Zang and Chenghao Yang.

## Requirements

- tensorflow-gpu == 1.14.0   

- keras == 2.2.4   

- sklearn == 0.0  

- anytree == 2.6.0  

- nltk == 3.4.5  

- OpenHowNet == 0.0.1a8    

- pytorch_transformers == 1.0.0  

- loguru == 0.3.2

## General Required Data and Tools

- Download [Glove vectors](http://nlp.stanford.edu/data/glove.840B.300d.zip)

- Download [Stanford POS Tagger](https://nlp.stanford.edu/software/tagger.shtml#Download)

## Reproducibility Support

Since data processing and models training may take a lot of time and computing resources, we provide the data and models we use for experiments. You can directly download the data and models we used for IMDB-related experiments from [TsinghuaCloud](https://cloud.tsinghua.edu.cn/d/b6b35b7b7fdb43c1bf8c/). The instructions of how to use these files can be found in the `README.md` files in `IMDB/`, `SNLI/` and `SST/`.

## Running Instructions

Please see the `README.md` files in `IMDB/`, `SNLI/` and `SST/` for specific running instructions for each attack models on corresponding downstream tasks.