pyrit.prompt_converter.PersuasionConverter

pyrit.prompt_converter.PersuasionConverter#

class PersuasionConverter(*, converter_target: PromptChatTarget = REQUIRED_VALUE, persuasion_technique: str)[source]#

Bases: PromptConverter

Rephrases prompts using a variety of persuasion techniques.

Based on https://arxiv.org/abs/2401.06373 by Zeng et al.

Supported persuasion techniques:
  • “authority_endorsement”:

    Citing authoritative sources in support of a claim.

  • “evidence_based”:

    Using empirical data, statistics, and facts to support a claim or decision.

  • “expert_endorsement”:

    Citing domain experts in support of a claim.

  • “logical_appeal”:

    Using logic or reasoning to support a claim.

  • “misrepresentation”:

    Presenting oneself or an issue in a way that’s not genuine or true.

__init__(*, converter_target: PromptChatTarget = REQUIRED_VALUE, persuasion_technique: str)[source]#

Initialize the converter with the specified target and prompt template.

Parameters:

  • converter_target (PromptChatTarget) – The chat target used to perform rewriting on user prompts. Can be omitted if a default has been configured via PyRIT initialization.

  • persuasion_technique (str) – Persuasion technique to be used by the converter, determines the system prompt to be used to generate new prompts. Must be one of “authority_endorsement”, “evidence_based”, “expert_endorsement”, “logical_appeal”, “misrepresentation”.

Raises:

  • ValueError – If converter_target is not provided and no default has been configured.

  • ValueError – If the persuasion technique is not supported or does not exist.

Methods

__init__(*[, converter_target])

Initialize the converter with the specified target and prompt template.

convert_async(*, prompt[, input_type])

Convert the given prompt using the persuasion technique specified during initialization.

convert_tokens_async(*, prompt[, ...])

Convert substrings within a prompt that are enclosed by specified start and end tokens.

get_identifier()

Return an identifier dictionary for the converter.

input_supported(input_type)

Check if the input type is supported by the converter.

output_supported(output_type)

Check if the output type is supported by the converter.

send_persuasion_prompt_async(request)

Send the prompt to the converter target and process the response.

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', 'binary_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', 'binary_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: Literal['text', 'image_path', 'audio_path', 'video_path', 'binary_path', 'url', 'reasoning', 'error', 'function_call', 'tool_call', 'function_call_output'] = 'text') → ConverterResult[source]#

Convert the given prompt using the persuasion technique specified during initialization.

Parameters:

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

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

Returns:

The result containing the converted prompt text.

Return type:

ConverterResult

Raises:

ValueError – If the input type is not supported.

async send_persuasion_prompt_async(request: Message) → str[source]#

Send the prompt to the converter target and process the response.

Parameters:

request (Message) – The message containing the prompt to be converted.

Returns:

The converted prompt text extracted from the response.

Return type:

str

Raises:

InvalidJsonException – If the response is not valid JSON or missing expected keys.

Contents