mirror of
https://github.com/QData/TextAttack.git
synced 2021-10-13 00:05:06 +03:00
81 lines
3.0 KiB
ReStructuredText
81 lines
3.0 KiB
ReStructuredText
Attack Recipes
|
|
===============
|
|
|
|
We provide a number of pre-built attack recipes. To run an attack recipe, run::
|
|
|
|
textattack attack --recipe [recipe_name]
|
|
|
|
Alzantot Genetic Algorithm (Generating Natural Language Adversarial Examples)
|
|
###################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.genetic_algorithm_alzantot_2018
|
|
:members:
|
|
|
|
Faster Alzantot Genetic Algorithm (Certified Robustness to Adversarial Word Substitutions)
|
|
##############################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.faster_genetic_algorithm_jia_2019
|
|
:members:
|
|
|
|
BAE (BAE: BERT-Based Adversarial Examples)
|
|
#############################################
|
|
|
|
.. automodule:: textattack.attack_recipes.bae_garg_2019
|
|
:members:
|
|
|
|
BERT-Attack: (BERT-Attack: Adversarial Attack Against BERT Using BERT)
|
|
#########################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.bert_attack_li_2020
|
|
:members:
|
|
|
|
DeepWordBug (Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers)
|
|
######################################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.deepwordbug_gao_2018
|
|
:members:
|
|
|
|
HotFlip (HotFlip: White-Box Adversarial Examples for Text Classification)
|
|
##############################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.hotflip_ebrahimi_2017
|
|
:members:
|
|
|
|
Input Reduction
|
|
################
|
|
|
|
.. automodule:: textattack.attack_recipes.input_reduction_feng_2018
|
|
:members:
|
|
|
|
Kuleshov (Adversarial Examples for Natural Language Classification Problems)
|
|
##############################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.kuleshov_2017
|
|
:members:
|
|
|
|
PWWS (Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency)
|
|
###################################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.pwws_ren_2019
|
|
:members:
|
|
|
|
Seq2Sick (Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples)
|
|
#########################################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.seq2sick_cheng_2018_blackbox
|
|
:members:
|
|
|
|
|
|
TextFooler (Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment)
|
|
########################################################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.textfooler_jin_2019
|
|
:members:
|
|
|
|
|
|
TextBugger (TextBugger: Generating Adversarial Text Against Real-world Applications)
|
|
########################################################################################
|
|
|
|
.. automodule:: textattack.attack_recipes.textbugger_li_2018
|
|
:members:
|