Fibber is a benchmarking suite for adversarial attacks on text classification.

## Project description

An open source project from Data to AI Lab at MIT.

# Fibber

Fibber is a library to evaluate different strategies to paraphrase natural language, especially how these strategies can break text classifiers without changing the meaning of a sentence.

# Overview

Fibber is a library to evaluate different strategies to paraphrase natural language. In this library, we have several built-in paraphrasing strategies. We also have a benchmark framework to evaluate the quality of paraphrase. In particular, we use the GPT2 language model to measure how meaningful is the paraphrased text. We use a universal sentence encoder to evaluate the semantic similarity between original and paraphrased text. We also train a BERT classifier on the original dataset, and check of paraphrased sentences can break the text classifier.

# Install

## Requirements

fibber has been developed and tested on Python 3.6, 3.7 and 3.8

Also, although it is not strictly required, the usage of conda is highly recommended to avoid interfering with other software installed in the system in which fibber is run.

These are the minimum commands needed to create a conda environment using python3.6 for fibber:

# First you should install conda.
conda create -n fibber_env python=3.6


Afterward, you have to execute this command to activate the environment:

conda activate fibber_env


Then you should install tensorflow and pytorch. Please follow the instructions for tensorflow and pytorch. Fibber requires tensorflow>=2.0.0 and pytorch>=1.5.0. Please choose a proper version of tensorflow and pytorch according to the CUDA version on your computer.

Remember to execute conda activate fibber_env every time you start a new console to work on fibber!

## Install from PyPI

After creating the conda environment and activating it, we recommend using pip in order to install fibber:

pip install fibber


This will pull and install the latest stable release from PyPI.

## Use without install

If you are using this project for research purpose and want to make changes to the code, you can install all requirements by

git clone git@github.com:DAI-Lab/fibber.git
cd fibber
pip install --requirement requirement.txt


Then you can use fibber by

python -m fibber.datasets.download_datasets
python -m fibber.benchmark.benchmark


In this case, any changes you made on the code will take effect immediately.

## Install from source

With your conda environment activated, you can clone the repository and install it from source by running make install on the stable branch:

git clone git@github.com:DAI-Lab/fibber.git
cd fibber
git checkout stable
make install


# Quickstart

In this short tutorial, we will guide you through a series of steps that will help you getting started with fibber.

(1) Install Fibber

(2) Get a demo dataset and resources.

from fibber.datasets import get_demo_dataset

trainset, testset = get_demo_dataset()



(3) Create a Fibber object.

from fibber.fibber import Fibber

# args starting with "bs_" are hyperparameters for the BertSamplingStrategy.
arg_dict = {
"use_gpu_id": 0,
"gpt2_gpu_id": 0,
"bert_gpu_id": 0,
"strategy_gpu_id": 0,
"bs_block_size": 3,
"bs_wpe_weight": 10000,
"bs_use_weight": 1000,
"bs_gpt2_weight": 10,
"bs_clf_weight": 3
}

# create a fibber object.
# This step may take a while (about 1 hour) on RTX TITAN, and requires 20G of
# GPU memory. If there's not enough GPU memory on your GPU, consider assign use
# gpt2, bert, and strategy to different GPUs.
#
fibber = Fibber(arg_dict, dataset_name="demo", strategy_name="BertSamplingStrategy",
trainset=trainset, testset=testset, output_dir="exp-demo")


The following command can randomly paraphrase the sentence into 5 different ways.

# Try sentences you like.
# label 0 means negative, and 1 means positive.
fibber.paraphrase(
{"text0": ("The Avengers is a good movie. Although it is 3 hours long, every scene has something to watch."),
"label": 1},
field_name="text0",
n=5)


The output is a tuple of (str, list, list).

# Original Text
'The Avengers is a good movie. Although it is 3 hours long, every scene has something to watch.'

# 5 paraphrases
['the avengers is a good movie. even it is 2 hours long, there is not enough to watch.',
'the avengers is a good movie. while it is 3 hours long, it is still very watchable.',
'the avengers is a good movie and although it is 2 ¹⁄₂ hours long, it is never very interesting.',
'avengers is not a good movie. while it is three hours long, it is still something to watch.',
'the avengers is a bad movie. while it is three hours long, it is still something to watch.']

# Evaluation metrics of these 5 paraphrases.

{'EditingDistance': 8,
'USESemanticSimilarity': 0.9523628950119019,
'GloVeSemanticSimilarity': 0.9795315341042675,
'GPT2GrammarQuality': 1.492070198059082,
'BertClfPrediction': 0},
{'EditingDistance': 9,
'USESemanticSimilarity': 0.9372092485427856,
'GloVeSemanticSimilarity': 0.9575780832312993,
'GPT2GrammarQuality': 0.9813404679298401,
'BertClfPrediction': 1},
{'EditingDistance': 11,
'USESemanticSimilarity': 0.9265919327735901,
'GloVeSemanticSimilarity': 0.9710499628056698,
'GPT2GrammarQuality': 1.325406551361084,
'BertClfPrediction': 0},
{'EditingDistance': 7,
'USESemanticSimilarity': 0.8913971185684204,
'GloVeSemanticSimilarity': 0.9800737898362042,
'GPT2GrammarQuality': 1.2504483461380005,
'BertClfPrediction': 1},
{'EditingDistance': 8,
'USESemanticSimilarity': 0.9124080538749695,
'GloVeSemanticSimilarity': 0.9744155151490856,
'GPT2GrammarQuality': 1.1626977920532227,
'BertClfPrediction': 0}]


(5) You can ask fibber to randomly pick a sentence from the dataset and paraphrase it.

fibber.paraphrase_a_random_sentence(n=5)


# Supported strategies

In this version, we implement three strategies

• IdentityStrategy:
• The identity strategy outputs the original text as its paraphrase.
• This strategy generates exactly 1 paraphrase for each original text regardless of --num_paraphrases_per_text flag.
• RandomStrategy:
• The random strategy outputs the random shuffle of words in the original text.
• TextFoolerStrategy:
• BertSamplingStrategy:

# What's next?

For more details about fibber and all its possibilities and features, please check the documentation site.

# History

## version 0.1.0

This release is a major update to Fibber library. Advanced paraphrase algorithms are included.

• Add two strategies: TextFoolerStrategy and BertSamplingStrategy.
• Improve the benchmarking framework: add more metrics specifically designed for adversarial attack.
• Datasets: add a variation of AG's news dataset, ag_no_title.
• Bug fix and improvements.

## version 0.0.1

This is the first release of Fibber library. This release contains:

• Datasets: fibber contains 6 built-in datasets.
• Metrics: fibber contains 6 metrics to evaluate the quality of paraphrased sentences. All metrics have a unified interface.
• Benchmark framework: the benchmark framework and easily evaluate the phraphrase strategies on built-in datasets and metrics.
• Strategies: this release contains 2 basic strategies, the identity strategy and random strategy.
• A unified Fibber interface: users can easily use fibber by creating a Fibber object.

## Project details

Uploaded source
Uploaded py2 py3