textattack.goal_functions package

Goal Functions

Goal Functions determine if an attack has been successful.

• textattack.goal_functions.classification package
  • Goal fucntion for Classification
  • Determine for if an attack has been successful in Classification
  • ClassificationGoalFunction
    • ClassificationGoalFunction.extra_repr_keys()
  • Determine if maintaining the same predicted label (input reduction)
  • InputReduction
    • InputReduction.extra_repr_keys()
  • Determine if an attack has been successful in targeted Classification
  • TargetedClassification
    • TargetedClassification.extra_repr_keys()
  • Determine successful in untargeted Classification
  • UntargetedClassification
• textattack.goal_functions.text package
  • Goal Function for Text to Text case
  • Goal Function for Attempts to minimize the BLEU score
  • MinimizeBleu
    • MinimizeBleu.clear_cache()
    • MinimizeBleu.extra_repr_keys()
    • MinimizeBleu.EPS
  • get_bleu()
  • Goal Function for seq2sick
  • NonOverlappingOutput
    • NonOverlappingOutput.clear_cache()
  • get_words_cached()
  • word_difference_score()
  • Goal Function for TextToText
  • TextToTextGoalFunction

GoalFunction Class

class textattack.goal_functions.goal_function.GoalFunction(model_wrapper, maximizable=False, use_cache=True, query_budget=inf, model_batch_size=32, model_cache_size=1048576)

Bases: ReprMixin, ABC

Evaluates how well a perturbed attacked_text object is achieving a specified goal.

Parameters:

• model_wrapper (ModelWrapper) – The victim model to attack.

• maximizable (bool, optional, defaults to False) – Whether the goal function is maximizable, as opposed to a boolean result of success or failure.

• query_budget (float, optional, defaults to float("in")) – The maximum number of model queries allowed.

• model_cache_size (int, optional, defaults to 2**20) – The maximum number of items to keep in the model results cache at once.

clear_cache()

extra_repr_keys()

Extra fields to be included in the representation of a class.

get_output(attacked_text)

Returns output for display based on the result of calling the model.

get_result(attacked_text, **kwargs)

A helper method that queries self.get_results with a single AttackedText object.

get_results(attacked_text_list, check_skip=False)

For each attacked_text object in attacked_text_list, returns a result consisting of whether or not the goal has been achieved, the output for display purposes, and a score.

Additionally returns whether the search is over due to the query budget.

init_attack_example(attacked_text, ground_truth_output)

Called before attacking attacked_text to ‘reset’ the goal function and set properties for this example.