如何使用OpenAttack进行文本对抗攻击

pip install OpenAttack

git clone https://github.com/thunlp/OpenAttack.git
cd OpenAttack
python setup.py install

import OpenAttack as oa
# choose a trained victim classification model
victim = oa.DataManager.load("Victim.BERT.SST")
# choose an evaluation dataset
dataset = oa.DataManager.load("Dataset.SST.sample")
# choose Genetic as the attacker and initialize it with default parameters
attacker = oa.attackers.GeneticAttacker()
# prepare for attacking
attack_eval = oa.attack_evals.DefaultAttackEval(attacker, victim)
# launch attacks and print attack results
attack_eval.eval(dataset, visualize=True)

import OpenAttack as oa
import numpy as np
from nltk.sentiment.vader import SentimentIntensityAnalyzer


# configure access interface of the customized victim model
class MyClassifier(oa.Classifier):
    def __init__(self):
        self.model = SentimentIntensityAnalyzer()
    # access to the classification probability scores with respect input sentences
    def get_prob(self, input_):
        rt = []
        for sent in input_:
            rs = self.model.polarity_scores(sent)
            prob = rs["pos"] / (rs["neg"] + rs["pos"])
            rt.append(np.array([1 - prob, prob]))
        return np.array(rt)
# choose the costomized classifier as the victim model
victim = MyClassifier()
# choose an evaluation dataset
dataset = oa.DataManager.load("Dataset.SST.sample")
# choose Genetic as the attacker and initialize it with default parameters
attacker = oa.attackers.GeneticAttacker()
# prepare for attacking
attack_eval = oa.attack_evals.DefaultAttackEval(attacker, victim)
# launch attacks and print attack results
attack_eval.eval(dataset, visualize=True)