pyrit.orchestrator.TreeOfAttacksWithPruningOrchestrator

pyrit.orchestrator.TreeOfAttacksWithPruningOrchestrator#

class TreeOfAttacksWithPruningOrchestrator(*, objective_target: PromptTarget, adversarial_chat: PromptChatTarget, scoring_target: PromptChatTarget, adversarial_chat_seed_prompt: SeedPrompt | None = None, adversarial_chat_system_prompt_path: Path | None = None, width: int = 3, depth: int = 5, branching_factor: int = 2, on_topic_checking_enabled: bool = True, prompt_converters: list[PromptConverter] | None = None, objective_achieved_score_threshold: float = 0.8, verbose: bool = False)[source]#

Bases: MultiTurnOrchestrator

__init__(*, objective_target: PromptTarget, adversarial_chat: PromptChatTarget, scoring_target: PromptChatTarget, adversarial_chat_seed_prompt: SeedPrompt | None = None, adversarial_chat_system_prompt_path: Path | None = None, width: int = 3, depth: int = 5, branching_factor: int = 2, on_topic_checking_enabled: bool = True, prompt_converters: list[PromptConverter] | None = None, objective_achieved_score_threshold: float = 0.8, verbose: bool = False) → None[source]#

Methods

__init__(*, objective_target, ...[, ...])

dispose_db_engine()

Dispose database engine to release database connections and resources.

get_identifier()

get_memory()

Retrieves the memory associated with this orchestrator.

get_score_memory()

Retrieves the scores of the PromptRequestPieces associated with this orchestrator.

run_attack_async(*, objective[, memory_labels])

Applies the TAP attack strategy asynchronously.

run_attacks_async(*, objectives[, ...])

Applies the attack strategy for each objective in the list of objectives.
async run_attack_async(*, objective: str, memory_labels: dict[str, str] | None = None) → TAPAttackResult[source]#

Applies the TAP attack strategy asynchronously.

Parameters:

  • objective (str) – The specific goal the orchestrator aims to achieve through the conversation.

  • memory_labels (dict[str, str], Optional) – A free-form dictionary of additional labels to apply to the prompts throughout the attack. Any labels passed in will be combined with self._global_memory_labels (from the GLOBAL_MEMORY_LABELS environment variable) into one dictionary. In the case of collisions, the passed-in labels take precedence. Defaults to None.

Returns:

Contains the outcome of the attack, including:

  • conversation_id (UUID): The ID associated with the final conversation state.

  • achieved_objective (bool): Indicates whether the orchestrator successfully met the objective.

  • objective (str): The intended goal of the attack.

Return type:

MultiTurnAttackResult