Skip to content

attack_recipes.rst

Latest commit

 

History

History
167 lines (93 loc) · 4.41 KB

attack_recipes.rst

File metadata and controls

167 lines (93 loc) · 4.41 KB

Attack Recipes API

We provide a number of pre-built attack recipes, which correspond to attacks from the literature. To run an attack recipe from the command line, run:

textattack attack --recipe [recipe_name]

To initialize an attack in Python script, use:

<recipe name>.build(model_wrapper)

For example, attack = InputReductionFeng2018.build(model) creates attack, an object of type Attack with the goal function, transformation, constraints, and search method specified in that paper. This object can then be used just like any other attack; for example, by calling attack.attack_dataset.

TextAttack supports the following attack recipes (each recipe's documentation contains a link to the corresponding paper):

Attacks on classification models

  1. A2T (Towards Improving Adversarial Training of NLP Models" (Yoo et al., 2021))
  2. Alzantot Genetic Algorithm (Generating Natural Language Adversarial Examples)
  3. Faster Alzantot Genetic Algorithm (Certified Robustness to Adversarial Word Substitutions)
  4. BAE (BAE: BERT-Based Adversarial Examples)
  5. BERT-Attack: (BERT-Attack: Adversarial Attack Against BERT Using BERT)
  6. CheckList: (Beyond Accuracy: Behavioral Testing of NLP models with CheckList)
  7. DeepWordBug (Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers)
  8. HotFlip (HotFlip: White-Box Adversarial Examples for Text Classification)
  9. Improved Genetic Algorithm (Natural Language Adversarial Attacks and Defenses in Word Level)
  10. Input Reduction (Pathologies of Neural Models Make Interpretations Difficult)
  11. Kuleshov (Adversarial Examples for Natural Language Classification Problems)
  12. Particle Swarm Optimization (Word-level Textual Adversarial Attacking as Combinatorial Optimization)
  13. PWWS (Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency)
  14. TextFooler (Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment)
  15. TextBugger (TextBugger: Generating Adversarial Text Against Real-world Applications)
  16. Pruthi (Combating Adversarial Misspellings with Robust Word Recognition 2019)
  17. CLARE (Contextualized Perturbation for Textual Adversarial Attack 2020)
  18. LEAP (LEAP: Efficient and Automated Test Method for NLP Software 2023)
.. automodule:: textattack.attack_recipes.a2t_yoo_2021
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.genetic_algorithm_alzantot_2018
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.faster_genetic_algorithm_jia_2019
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.bae_garg_2019
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.bert_attack_li_2020
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.checklist_ribeiro_2020
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.deepwordbug_gao_2018
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.hotflip_ebrahimi_2017
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.iga_wang_2019
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.input_reduction_feng_2018
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.kuleshov_2017
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.pso_zang_2020
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.pwws_ren_2019
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.textfooler_jin_2019
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.textbugger_li_2018
   :members:
   :noindex:






.. automodule:: textattack.attack_recipes.clare_li_2020
   :members:
   :noindex:




.. automodule:: textattack.attack_recipes.pruthi_2019
   :members:
   :noindex:


.. automodule:: textattack.attack_recipes.leap_2023
   :members:
   :noindex:

Attacks on sequence-to-sequence models

  1. MORPHEUS (It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations)
  2. Seq2Sick (Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples)
.. automodule:: textattack.attack_recipes.morpheus_tan_2020
   :members:
   :noindex:



.. automodule:: textattack.attack_recipes.seq2sick_cheng_2018_blackbox
   :members:
   :noindex: