Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
ZGY bfedfa74f3 | 2 years ago | |
---|---|---|
.github/workflows | 3 years ago | |
OpenAttack | 2 years ago | |
docs | 2 years ago | |
examples | 2 years ago | |
slow_tests | 2 years ago | |
test | 2 years ago | |
.gitignore | 2 years ago | |
LICENSE | 3 years ago | |
README.md | 2 years ago | |
build-doc.py | 2 years ago | |
build-doc.sh | 3 years ago | |
demo.py | 2 years ago | |
demo_chinese.py | 2 years ago | |
demo_deo.py | 2 years ago | |
pyproject.toml | 4 years ago | |
requirements-dev.txt | 2 years ago | |
requirements-doc.txt | 2 years ago | |
requirements.txt | 2 years ago | |
setup.py | 3 years ago |
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.
⭐️ Support for all attack types. OpenAttack supports all types of attacks including sentence-/word-/character-level perturbations and gradient-/score-/decision-based/blind attack models;
⭐️ Multilinguality. OpenAttack supports English and Chinese now. Its extensible design enables quick support for more languages;
⭐️ Parallel processing. OpenAttack provides support for multi-process running of attack models to improve attack efficiency;
⭐️ Compatibility with 🤗 Hugging Face. OpenAttack is fully integrated with 🤗 Transformers and Datasets libraries;
⭐️ Great extensibility. You can easily attack a customized victim model on any customized dataset or develop and evaluate a customized attack model.
✅ Providing various handy baselines for attack models;
✅ Comprehensively evaluating attack models using its thorough evaluation metrics;
✅ Assisting in quick development of new attack models with the help of its common attack components;
✅ Evaluating the robustness of a machine learning model against various adversarial attacks;
✅ Conducting adversarial training to improve robustness of a machine learning model by enriching the training data with generated adversarial examples.
pip
(recommended)pip install OpenAttack
git clone https://github.com/thunlp/OpenAttack.git
cd OpenAttack
python setup.py install
After installation, you can try running demo.py
to check if OpenAttack works well:
python demo.py
OpenAttack builds in some commonly used NLP models like BERT (Devlin et al. 2018) and RoBERTa (Liu et al. 2019) that have been fine-tuned on some commonly used datasets (such as SST-2). You can effortlessly conduct adversarial attacks against these built-in victim models.
The following code snippet shows how to use PWWS, a greedy algorithm-based attack model (Ren et al., 2019), to attack BERT on the SST-2 dataset (the complete executable code is here).
import OpenAttack as oa
import datasets # use the Hugging Face's datasets library
# change the SST dataset into 2-class
def dataset_mapping(x):
return {
"x": x["sentence"],
"y": 1 if x["label"] > 0.5 else 0,
}
# choose a trained victim classification model
victim = oa.DataManager.loadVictim("BERT.SST")
# choose 20 examples from SST-2 as the evaluation data
dataset = datasets.load_dataset("sst", split="train[:20]").map(function=dataset_mapping)
# choose PWWS as the attacker and initialize it with default parameters
attacker = oa.attackers.PWWSAttacker()
# prepare for attacking
attack_eval = OpenAttack.AttackEval(attacker, victim)
# launch attacks and print attack results
attack_eval.eval(dataset, visualize=True)
The following code snippet shows how to use PWWS to attack a customized sentiment analysis model (a statistical model built in NLTK) on SST-2 (the complete executable code is here).
import OpenAttack as oa
import numpy as np
import datasets
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
# configure access interface of the customized victim model by extending OpenAttack.Classifier.
class MyClassifier(oa.Classifier):
def __init__(self):
# nltk.sentiment.vader.SentimentIntensityAnalyzer is a traditional sentiment classification model.
nltk.download('vader_lexicon')
self.model = SentimentIntensityAnalyzer()
def get_pred(self, input_):
return self.get_prob(input_).argmax(axis=1)
# access to the classification probability scores with respect input sentences
def get_prob(self, input_):
ret = []
for sent in input_:
# SentimentIntensityAnalyzer calculates scores of “neg” and “pos” for each instance
res = self.model.polarity_scores(sent)
# we use 𝑠𝑜𝑐𝑟𝑒_𝑝𝑜𝑠 / (𝑠𝑐𝑜𝑟𝑒_𝑛𝑒𝑔 + 𝑠𝑐𝑜𝑟𝑒_𝑝𝑜𝑠) to represent the probability of positive sentiment
# Adding 10^−6 is a trick to avoid dividing by zero.
prob = (res["pos"] + 1e-6) / (res["neg"] + res["pos"] + 2e-6)
ret.append(np.array([1 - prob, prob]))
# The get_prob method finally returns a np.ndarray of shape (len(input_), 2). See Classifier for detail.
return np.array(ret)
def dataset_mapping(x):
return {
"x": x["sentence"],
"y": 1 if x["label"] > 0.5 else 0,
}
# load some examples of SST-2 for evaluation
dataset = datasets.load_dataset("sst", split="train[:20]").map(function=dataset_mapping)
# choose the costomized classifier as the victim model
victim = MyClassifier()
# choose PWWS as the attacker and initialize it with default parameters
attacker = oa.attackers.PWWSAttacker()
# prepare for attacking
attack_eval = oa.AttackEval(attacker, victim)
# launch attacks and print attack results
attack_eval.eval(dataset, visualize=True)
The following code snippet shows how to use PWWS to attack an existing fine-tuned sentiment analysis model on a customized dataset (the complete executable code is here).
import OpenAttack as oa
import transformers
import datasets
# load a fine-tuned sentiment analysis model from Transformers (you can also use our fine-tuned Victim.BERT.SST)
tokenizer = transformers.AutoTokenizer.from_pretrained("echarlaix/bert-base-uncased-sst2-acc91.1-d37-hybrid")
model = transformers.AutoModelForSequenceClassification.from_pretrained("echarlaix/bert-base-uncased-sst2-acc91.1-d37-hybrid", num_labels=2, output_hidden_states=False)
victim = oa.classifiers.TransformersClassifier(model, tokenizer, model.bert.embeddings.word_embeddings)
# choose PWWS as the attacker and initialize it with default parameters
attacker = oa.attackers.PWWSAttacker()
# create your customized dataset
dataset = datasets.Dataset.from_dict({
"x": [
"I hate this movie.",
"I like this apple."
],
"y": [
0, # 0 for negative
1, # 1 for positive
]
})
# prepare for attacking
attack_eval = oa.AttackEval(attacker, victim, metrics = [oa.metric.EditDistance(), oa.metric.ModificationRate()])
# launch attacks and print attack results
attack_eval.eval(dataset, visualize=True)
OpenAttack supports convenient multiprocessing to accelerate the process of adversarial attacks. The following code snippet shows how to use multiprocessing in adversarial attacks with Genetic (Alzantot et al. 2018), a genetic algorithm-based attack model (the complete executable code is here).
import OpenAttack as oa
import datasets
def dataset_mapping(x):
return {
"x": x["sentence"],
"y": 1 if x["label"] > 0.5 else 0,
}
victim = oa.loadVictim("BERT.SST")
dataset = datasets.load_dataset("sst", split="train[:20]").map(function=dataset_mapping)
attacker = oa.attackers.GeneticAttacker()
attack_eval = oa.AttackEval(attacker, victim)
# Using multiprocessing simply by specify num_workers
attack_eval.eval(dataset, visualize=True, num_workers=4)
OpenAttack now supports adversarial attacks against English and Chinese victim models. Here is an example code of conducting adversarial attacks against a Chinese review classification model using PWWS.
OpenAttack incorporates many handy components that can be easily assembled into new attack models. Here gives an example of how to design a simple attack model that shuffles the tokens in the original sentence.
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 gives an example of how to conduct adversarial training with OpenAttack.
Attack Sentence Pair Classification Models. In addition to single sentence classification models, OpenAttack support attacks against sentence pair classification models. Here is an example code of conducting adversarial attacks against an NLI model with OpenAttack.
Customized Evaluation Metric. OpenAttack supports designing a customized adversarial attack evaluation metric. Here gives an example of how to add a customized evaluation metric and use it to evaluate adversarial attacks.
According to the level of perturbations imposed on original input, textual adversarial attack models can be categorized into sentence-level, word-level, character-level attack models.
According to the accessibility to the victim model, textual adversarial attack models can be categorized into gradient
-based, score
-based, decision
-based and blind
attack models.
TAADPapers is a paper list which summarizes almost all the papers concerning textual adversarial attack and defense. You can have a look at this list to find more attack models.
Currently OpenAttack includes 15 typical attack models against text classification models that cover all attack types.
Here is the list of currently involved attack models.
decision
[pdf] [code]blind
[pdf] [code&data]decision
[pdf] [code]score
[pdf] [code]score
[pdf] [code]score
[pdf] [code]score
[pdf] [code]score
[pdf] [code]score
[pdf] [code]gradient
[pdf]gradient
score
[pdf]gradient
[pdf] [code] [website]gradient
[pdf] [code]score
[pdf] [code&data]score
[pdf] [code]The following table illustrates the comparison of the attack models.
Model | Accessibility | Perturbation | Main Idea |
---|---|---|---|
SEA | Decision | Sentence | Rule-based paraphrasing |
SCPN | Blind | Sentence | Paraphrasing |
GAN | Decision | Sentence | Text generation by encoder-decoder |
TextFooler | Score | Word | Greedy word substitution |
PWWS | Score | Word | Greedy word substitution |
Genetic | Score | Word | Genetic algorithm-based word substitution |
SememePSO | Score | Word | Particle Swarm Optimization-based word substitution |
BERT-ATTACK | Score | Word | Greedy contextualized word substitution |
BAE | Score | Word | Greedy contextualized word substitution and insertion |
FD | Gradient | Word | Gradient-based word substitution |
TextBugger | Gradient, Score | Word+Char | Greedy word substitution and character manipulation |
UAT | Gradient | Word, Char | Gradient-based word or character manipulation |
HotFlip | Gradient | Word, Char | Gradient-based word or character substitution |
VIPER | Blind | Char | Visually similar character substitution |
DeepWordBug | Score | Char | Greedy character manipulation |
Considering the significant distinctions among different attack models, we leave considerable freedom for the skeleton design of attack models, and focus more on streamlining the general processing of adversarial attacking and the common components used in attack models.
OpenAttack has 7 main modules:
Please cite our paper if you use this toolkit:
@inproceedings{zeng2020openattack,
title={{Openattack: An open-source textual adversarial attack toolkit}},
author={Zeng, Guoyang and Qi, Fanchao and Zhou, Qianrui and Zhang, Tingji and Hou, Bairu and Zang, Yuan and Liu, Zhiyuan and Sun, Maosong},
booktitle={Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations},
pages={363--371},
year={2021},
url={https://aclanthology.org/2021.acl-demo.43},
doi={10.18653/v1/2021.acl-demo.43}
}
We thank all the contributors to this project. And more contributions are very welcome.
No Description
Python other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》