pyrit.prompt_converter.UnicodeConfusableConverter

class UnicodeConfusableConverter(*, source_package: Literal['confusable_homoglyphs', 'confusables'] = 'confusable_homoglyphs', deterministic: bool = False)

Bases: PromptConverter

Applies substitutions to words in the prompt to test adversarial textual robustness by replacing characters with visually similar ones.

__init__(*, source_package: Literal['confusable_homoglyphs', 'confusables'] = 'confusable_homoglyphs', deterministic: bool = False)

Initializes the converter with the specified source package for homoglyph generation.

Parameters:

• source_package (Literal["confusable_homoglyphs", "confusables"]) –

  The package to use for homoglyph generation.

  Can be either:

  • ”confusable_homoglyphs” (https://pypi.org/project/confusable-homoglyphs/):

    Used by default as it is more regularly maintained and up to date with the latest Unicode-provided confusables found here: https://www.unicode.org/Public/security/latest/confusables.txt

  • ”confusables” (https://pypi.org/project/confusables/):

    Provides additional methods of matching characters (not just Unicode list), so each character has more possible substitutions.

• deterministic (bool) – This argument is for unittesting only.

Methods

__init__(*[, source_package, deterministic])	Initializes the converter with the specified source package for homoglyph generation.
convert_async(*, prompt[, input_type])	Converts the given prompt by applying confusable substitutions.
convert_tokens_async(*, prompt[, ...])	Converts substrings within a prompt that are enclosed by specified start and end tokens.
get_identifier()	Returns an identifier dictionary for the converter.
input_supported(input_type)	Checks if the input type is supported by the converter.
output_supported(output_type)	Checks if the output type is supported by the converter.

Attributes

SUPPORTED_INPUT_TYPES	Tuple of input modalities supported by this converter.
SUPPORTED_OUTPUT_TYPES	Tuple of output modalities supported by this converter.
supported_input_types	Returns a list of supported input types for the converter.
supported_output_types	Returns a list of supported output types for the converter.

SUPPORTED_INPUT_TYPES: tuple[Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'], ...] = ('text',)

Tuple of input modalities supported by this converter. Subclasses must override this.

SUPPORTED_OUTPUT_TYPES: tuple[Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'], ...] = ('text',)

Tuple of output modalities supported by this converter. Subclasses must override this.

async convert_async(*, prompt: str, input_type='text') → ConverterResult

Converts the given prompt by applying confusable substitutions. This leads to a prompt that looks similar, but is actually different (e.g., replacing a Latin ‘a’ with a Cyrillic ‘а’).

Parameters:

• prompt (str) – The prompt to be converted.

• input_type (PromptDataType) – The type of input data.

Returns:

The result containing the prompt with confusable substitutions applied.

Return type:

ConverterResult

Raises:

ValueError – If the input type is not supported.