Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

Overview

StyleAttack

Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

Prepare Poison/Transfer Data

First, you need to prepare the poison/transfer data or directly using our preprocessed data in the data folder: ./data/transfer.

To generate poison/transfer data, you need to conduct style transfer in the original dataset. We implement it based on the code. Please move further to check the detail.

Backdoor Attack

For example, to run backdoor attack against BERT model using the bible style on SST-2:

CUDA_VISIBLE_DEVICES=0 python run_poison_bert.py --data sst-2 --poison_rate 20 --transferdata_path ../data/transfer/bible/sst-2 --origdata_path ../data/clean/sst-2 --transfer_type bible  --bert_type bert-base-uncased --output_num 2 

Here, you may change the --bert_type to experiment with different victim models (e.g. roberta-base, distilbert-base-uncased). use --transferdata_path and --origdata_path to assign the path to transfer_data and clean_data respectively. Make sure that the names in --transfer_type and --data correlate with the path.

If you want to experiment with other datasets, first perform style transfer following the code. Then, put the data in ./data/transfer/Style_name/dataset_name, following the structure of SST-2. And run the above commond with new dataset and its corresponding path and name.

Adversarial Attack

First, download the pre-trained Style-transfer models

For example, to run adversarial attack on SST-2:

CUDA_VISIBLE_DEVICES=0 python attack.py --model_name  textattack/bert-base-uncased-SST-2 --orig_file_path ../data/clean/sst-2/test.tsv --model_dir style_transfer_model_path --output_file_path record.log

Here, --model_name is the pre-trained model name in Hugging Face Models Zoo, --model_dir is the style_transfer_model_path, dwonloaded in the previous step. --orig_file_path is the path to original test set.

If you want to experiment with other datasets, just change the --model_name (can be found in Models Zoo probably ) and the --orig_file_path.

Owner
THUNLP
Natural Language Processing Lab at Tsinghua University
THUNLP
Seg-Torch for Image Segmentation with Torch

Seg-Torch for Image Segmentation with Torch This work was sparked by my personal research on simple segmentation methods based on deep learning. It is

Eren Gölge 37 Dec 12, 2022
Some toy examples of score matching algorithms written in PyTorch

toy_gradlogp This repo implements some toy examples of the following score matching algorithms in PyTorch: ssm-vr: sliced score matching with variance

Ending Hsiao 21 Dec 26, 2022
Self-Guided Contrastive Learning for BERT Sentence Representations

Self-Guided Contrastive Learning for BERT Sentence Representations This repository is dedicated for releasing the implementation of the models utilize

Taeuk Kim 16 Dec 04, 2022
Advanced yabai wooting scripts

Yabai Wooting scripts Installation requirements Both https://github.com/xiamaz/python-yabai-client and https://github.com/xiamaz/python-wooting-rgb ne

Max Zhao 3 Dec 31, 2021
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling Transformer-based models are widely used in natural language processi

Zhanpeng Zeng 12 Jan 01, 2023
PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction

Deep Networks from the Principle of Rate Reduction This repository is the official PyTorch implementation of the paper Deep Networks from the Principl

459 Dec 27, 2022
A motion detection system with RaspberryPi, OpenCV, Python

Human Detection System using Raspberry Pi Functionality Activates a relay on detecting motion. You may need following components to get the expected R

Omal Perera 55 Dec 04, 2022
Pytorch implementation of Generative Models as Distributions of Functions 🌿

Generative Models as Distributions of Functions This repo contains code to reproduce all experiments in Generative Models as Distributions of Function

Emilien Dupont 117 Dec 29, 2022
Paddle-Skeleton-Based-Action-Recognition - DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN

Paddle-Skeleton-Action-Recognition DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN. Yo

Chenxu Peng 3 Nov 02, 2022
Project for tracking occupancy in Tel-Aviv parking lots.

Ahuzat Dibuk - Tracking occupancy in Tel-Aviv parking lots main.py This module was set-up to be executed on Google Cloud Platform. I run it every 15 m

Geva Kipper 35 Nov 22, 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
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
Example Of Fine-Tuning BERT For Named-Entity Recognition Task And Preparing For Cloud Deployment Using Flask, React, And Docker

Example Of Fine-Tuning BERT For Named-Entity Recognition Task And Preparing For Cloud Deployment Using Flask, React, And Docker This repository contai

Nikita 12 Dec 14, 2022
Cl datasets - PyTorch image dataloaders and utility functions to load datasets for supervised continual learning

Continual learning datasets Introduction This repository contains PyTorch image

berjaoui 5 Aug 28, 2022
Neural style transfer in PyTorch.

style-transfer-pytorch An implementation of neural style transfer (A Neural Algorithm of Artistic Style) in PyTorch, supporting CPUs and Nvidia GPUs.

Katherine Crowson 395 Jan 06, 2023
Picasso: a methods for embedding points in 2D in a way that respects distances while fitting a user-specified shape.

Picasso Code to generate Picasso embeddings of any input matrix. Picasso maps the points of an input matrix to user-defined, n-dimensional shape coord

Pachter Lab 45 Dec 23, 2022
Experiments for Neural Flows paper

Neural Flows: Efficient Alternative to Neural ODEs [arxiv] TL;DR: We directly model the neural ODE solutions with neural flows, which is much faster a

54 Dec 07, 2022
KGDet: Keypoint-Guided Fashion Detection (AAAI 2021)

KGDet: Keypoint-Guided Fashion Detection (AAAI 2021) This is an official implementation of the AAAI-2021 paper "KGDet: Keypoint-Guided Fashion Detecti

Qian Shenhan 35 Dec 29, 2022
PyTorch implementation of Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Release Notes The official PyTorch implementation of Neural View S

Angtian Wang 20 Oct 09, 2022
Attention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)

Intro This repository contains code to generate data and reproduce experiments from our NeurIPS 2019 paper: Boris Knyazev, Graham W. Taylor, Mohamed R

Boris Knyazev 242 Jan 06, 2023