Skip to main content

A python package for attacking Russian NLP models

Project description

Robustness Evaluation of Pre-trained Language Models in the Russian Language

This is a repo with experiments for Robustness Evaluation of Pre-trained Language Models in the Russian Language and a tool ru_attacker for attacking Russian NLP models

Installation

pip install ru_attacker

Usage example

Set model

>>> from ru_attacker.models import RobertaModel
>>> roberta_checkpoints = "Roberta_checkpoints"
>>> ruRoberta = RobertaModel(roberta_checkpoints)

Set dataset

>>> from ru_attacker.models.set_dataset import get_data
>>> data_dir = "TERRa/val.jsonl" 
>>> data = get_data(data_dir)

Set attack

You have to define transformation, goal_function and type_perturbation. constraints and search_method are optional

>>> from ru_attacker.attacks.transformations import BackTranslation  # transformation
>>> from ru_attacker.attacks.goal_function import LabelPreserving  # goal function
>>> from ru_attacker.attacks.constraints import GrammarAcceptability, SemanticSimilarity  # constraints
>>> from ru_attacker.attacks.search_method import GreedySearch  # search method
>>> from ru_attacker.attacks import Attack  # attack wrapper
>>> backtranslation = Attack(
        transformation=BackTranslation(languages=["en", "fr", "de"]),  # you can set languages manually or use the default ones
        goal_function=LabelPreserving(),
        type_perturbation="hypothesis",  # to what part perturbation is applied {"hypothesis", "premise"}
        constraints=[GrammarAcceptability(), SemanticSimilarity()],
        search_method=GreedySearch()
    )

Attack model and view results

>>> results = backtranslation.attack(ruRoberta, data)
                  [Succeeded / Failed / Skipped / Total] 0 / 1 / 0 / 1:
                  entailment --> entailment
                  original premise: """Решение носит символический характер, так как взыскать компенсацию практически невозможно"", - отмечается в сообщении."
                  original hypothesis: Взыскать компенсацию не получится.

                  transformed: Компенсации не будет.

                  

                  [Succeeded / Failed / Skipped / Total] 1 / 1 / 0 / 2:
                  entailment --> not_entailment
                  original premise: Об этом вечером во вторник, 17 января, сообщила пресс-служба Спасательного департамента, отметив, что немецкую противотанковую мину Tellermine 42 обнаружили в на улице Кеэвисе в ходе земляных работ. Спасатели эвакуировали жителей окрестных домов, офисов и складских помещений. Уничтожать мину на месте не стали, поскольку это угрожало повреждению трассы трубопровода.
                  original hypothesis: На улице Кеэвисе жителей эвакуировали из-за мины.

                  transformed: На улице Касери эвакуировали жителей из мин.

Convert results to DataFrame

>>> import pandas as pd
>>> dataframe = pd.DataFrame(results)

Here is Tutorial

Experiments

All the data used in experiments and the results are in data folder (TERRa and results correspondingly).

All experiments can be reproduced in Experiments.ipynb.

Models checkpoints are available via:

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ru_attacker-0.0.5.tar.gz (14.7 kB view details)

Uploaded Source

Built Distribution

ru_attacker-0.0.5-py3-none-any.whl (27.9 kB view details)

Uploaded Python 3

File details

Details for the file ru_attacker-0.0.5.tar.gz.

File metadata

  • Download URL: ru_attacker-0.0.5.tar.gz
  • Upload date:
  • Size: 14.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.4.0 pkginfo/1.7.0 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.8.5

File hashes

Hashes for ru_attacker-0.0.5.tar.gz
Algorithm Hash digest
SHA256 5011870c41d84b940ea3320478ef0f43f40b9986e20edb4fc20969c03c8ff884
MD5 b9c327f81d9e553d326a3e49d26e4c2a
BLAKE2b-256 7d20c0e5926929ed91f4903efca141f0b23e8af5d6c1713301b99df4153ff4f5

See more details on using hashes here.

File details

Details for the file ru_attacker-0.0.5-py3-none-any.whl.

File metadata

  • Download URL: ru_attacker-0.0.5-py3-none-any.whl
  • Upload date:
  • Size: 27.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.4.0 pkginfo/1.7.0 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.8.5

File hashes

Hashes for ru_attacker-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 5138801118b7d093894740aed6cd95db7592086822274129e7150f382a165fcb
MD5 39ffed6c146e68834cdb1dc7cb3bca35
BLAKE2b-256 4f7a43415adc5ec0bfea2a8c7153e23392f432e065b51a7a11109c2f94c84c62

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page