Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021

Related tags

Deep LearningCLARE
Overview

Contextualized Perturbation for Textual Adversarial Attack

Introduction

This is a PyTorch implementation of Contextualized Perturbation for Textual Adversarial Attack by Dianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen, Chris Brockett, Ming-Ting Sun and Bill Dolan, NAACL 2021.

A third-party implementation of CLARE is available in the TextAttack.

Environment

The code is based on python 3.6, tensorflow 1.14 and Pytorch 1.4.0 version. The code is developed and tested using one NVIDIA GTX 1080Ti.

Please use Conda to setup your environment, and then run

conda install -y pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch

bash install_requirement.sh

Data Preparation and Pretrained Classifier

You can download pretrained target classifier and full training data in here (Coming soon). Alternatively, you can prepare you own training set in the same format as the example under /data/training_data/${dataset}/dataset/. The format will look like:

label text1 text2
2 At the end of 5 years ... The healthcare agency will be able ...

For single sentence classification, there is an empty field in text2.

After this, please run:

python train_BERT_classifier.py --dataset ${dataset} --save_model.

It will save pretrained classifer under the director: /saved_model/${dataset}_uncased/. The default target classifer is bert, you can train other types by setting extra argument: --target_model textcnn. Please check out the arguments in config.py for more details.

The text samples to be attacked are store in /data/${dataset}.tsv with the same format.

Textual Adversarial Attack

Simply run:

python bert_attack_classification.py --dataset ${dataset} --sample_file ${dataset}

and it will save the results under /adv_results/.

To attack qnli dataset, please add an argument --attack_second as we attack the longer sentence in two-sentence classification.

You can also modify the attacking hyper-parameters in hyper_parameters.py to adjust the trade-off between different aspects. Other details can be refered in config.py.

To run the attack from the baseline textfooler:

python attack_classification.py --dataset ${dataset} --sample_file ${dataset}

Citing

if you find our work is useful in your research, please consider citing:

@InProceedings{li2021contextualized,
  title={Contextualized perturbation for textual adversarial attack},
  author={Li, Dianqi and Zhang, Yizhe and Peng, Hao and Chen, Liqun and Brockett, Chris and Sun, Ming-Ting and Dolan, Bill},
  booktitle={Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics},
  year={2021}
}
Owner
cookielee77
Ph.D. candidate at University of Washington
cookielee77
Minimal fastai code needed for working with pytorch

fastai_minima A mimal version of fastai with the barebones needed to work with Pytorch #all_slow Install pip install fastai_minima How to use This lib

Zachary Mueller 14 Oct 21, 2022
EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow

EfficientDet This is an implementation of EfficientDet for object detection on Keras and Tensorflow. The project is based on the official implementati

1.3k Dec 19, 2022
SeqTR: A Simple yet Universal Network for Visual Grounding

SeqTR This is the official implementation of SeqTR: A Simple yet Universal Network for Visual Grounding, which simplifies and unifies the modelling fo

seanZhuh 76 Dec 24, 2022
CIFAR-10_train-test - training and testing codes for dataset CIFAR-10

CIFAR-10_train-test - training and testing codes for dataset CIFAR-10

Frederick Wang 3 Apr 26, 2022
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks

What is DeepHyper? DeepHyper is a software package that uses learning, optimization, and parallel computing to automate the design and development of

DeepHyper Team 214 Jan 08, 2023
Code for KDD'20 "Generative Pre-Training of Graph Neural Networks"

GPT-GNN: Generative Pre-Training of Graph Neural Networks GPT-GNN is a pre-training framework to initialize GNNs by generative pre-training. It can be

Ziniu Hu 346 Dec 19, 2022
An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

MetaICL: Learning to Learn In Context This includes an original implementation of "MetaICL: Learning to Learn In Context" by Sewon Min, Mike Lewis, Lu

Meta Research 141 Jan 07, 2023
[Preprint] "Bag of Tricks for Training Deeper Graph Neural Networks A Comprehensive Benchmark Study" by Tianlong Chen*, Kaixiong Zhou*, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, Zhangyang Wang

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Codes for [Preprint] Bag of Tricks for Training Deeper Graph

VITA 101 Dec 29, 2022
catch-22: CAnonical Time-series CHaracteristics

catch22 - CAnonical Time-series CHaracteristics About catch22 is a collection of 22 time-series features coded in C that can be run from Python, R, Ma

Carl H Lubba 229 Oct 21, 2022
The Noise Contrastive Estimation for softmax output written in Pytorch

An NCE implementation in pytorch About NCE Noise Contrastive Estimation (NCE) is an approximation method that is used to work around the huge computat

Kaiyu Shi 287 Nov 25, 2022
Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision

MLP Mixer Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision. Give us a star if you like this repo. Author: Github: bangoc123 Emai

Ngoc Nguyen Ba 86 Dec 10, 2022
Code to reproduce the results in "Visually Grounded Reasoning across Languages and Cultures", EMNLP 2021.

marvl-code [WIP] This is the implementation of the approaches described in the paper: Fangyu Liu*, Emanuele Bugliarello*, Edoardo M. Ponti, Siva Reddy

25 Nov 15, 2022
An ML & Correlation platform for transforming disparate data points of interest into usable intelligence.

SSIDprobeCollector An ML & Correlation platform for transforming disparate data points of interest into usable intelligence. At a High level the platf

Bill Reyor 1 Jan 30, 2022
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.

Introduction YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and ind

7.7k Jan 03, 2023
GAN JAX - A toy project to generate images from GANs with JAX

GAN JAX - A toy project to generate images from GANs with JAX This project aims to bring the power of JAX, a Python framework developped by Google and

Valentin Goldité 14 Nov 29, 2022
Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.

Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.

Stephen James 51 Dec 27, 2022
Repository for the paper : Meta-FDMixup: Cross-Domain Few-Shot Learning Guided byLabeled Target Data

1 Meta-FDMIxup Repository for the paper : Meta-FDMixup: Cross-Domain Few-Shot Learning Guided byLabeled Target Data. (ACM MM 2021) paper News! the rep

Fu Yuqian 44 Nov 18, 2022
Unofficial implementation of Fast-SCNN: Fast Semantic Segmentation Network

Fast-SCNN: Fast Semantic Segmentation Network Unofficial implementation of the model architecture of Fast-SCNN. Real-time Semantic Segmentation and mo

Philip Popien 69 Aug 11, 2022
Soomvaar is the repo which 🏩 contains different collection of 👨‍💻🚀code in Python and 💫✨Machine 👬🏼 learning algorithms📗📕 that is made during 📃 my practice and learning of ML and Python✨💥

Soomvaar 📌 Introduction Soomvaar is the collection of various codes implement in machine learning and machine learning algorithms with python on coll

Felix-Ayush 42 Dec 30, 2022
Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy"

Shapeland Simulator Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy" Download the video at https://www.youtube.com/watch?

TouringPlans.com 70 Dec 14, 2022