API Reference

Contents

API Reference#

`pyrit.analytics`#

ConversationAnalytics

Handles analytics operations on conversation data, such as finding similar chat messages based on conversation history or embedding similarity.

`pyrit.auth`#

`Authenticator`
`AzureAuth`	Azure CLI Authentication.
`AzureStorageAuth`	A utility class for Azure Storage authentication, providing methods to generate SAS tokens using user delegation keys.

`pyrit.auxiliary_attacks`#

`pyrit.chat_message_normalizer`#

`ChatMessageNormalizer`
`ChatMessageNop`
`GenericSystemSquash`
`ChatMessageNormalizerChatML`
`ChatMessageNormalizerTokenizerTemplate`	This class enables you to apply the chat template stored in a Hugging Face tokenizer to a list of chat messages.

`pyrit.common`#

`pyrit.datasets`#

`fetch_decoding_trust_stereotypes_examples`	Fetch DecodingTrust examples and create a SeedPromptDataset.
`fetch_examples`	Fetch examples from a specified source with caching support.
`fetch_harmbench_examples`	Fetch HarmBench examples and create a SeedPromptDataset.
`fetch_many_shot_jailbreaking_examples`	Fetch many-shot jailbreaking examples from a specified source.
`fetch_seclists_bias_testing_examples`	Fetch SecLists AI LLM Bias Testing examples from a specified source and create a SeedPromptDataset.
`fetch_xstest_examples`	Fetch XSTest examples and create a SeedPromptDataset.
`fetch_pku_safe_rlhf_dataset`	Fetch PKU-SafeRLHF examples and create a SeedPromptDataset.
`fetch_adv_bench_dataset`	Fetch AdvBench examples and create a SeedPromptDataset.
`fetch_wmdp_dataset`	Fetch WMDP examples and create a QuestionAnsweringDataset.
`fetch_forbidden_questions_df`	Fetch Forbidden question dataset and return it as a SeedPromptDataset
`fetch_llm_latent_adversarial_training_harmful_dataset`
`fetch_tdc23_redteaming_dataset`	Fetch TDC23-RedTeaming examples and create a SeedPromptDataset.

`pyrit.embedding`#

`AzureTextEmbedding`
`OpenAiTextEmbedding`

`pyrit.exceptions`#

`BadRequestException`	Exception class for bad client requests.
`EmptyResponseException`	Exception class for empty response errors.
`handle_bad_request_exception`
`InvalidJsonException`	Exception class for blocked content errors.
`MissingPromptPlaceholderException`	Exception class for missing prompt placeholder errors.
`PyritException`
`pyrit_json_retry`	A decorator to apply retry logic with exponential backoff to a function.
`pyrit_target_retry`	A decorator to apply retry logic with exponential backoff to a function.
`pyrit_placeholder_retry`	A decorator to apply retry logic.
`RateLimitException`	Exception class for authentication errors.
`remove_markdown_json`	Checks if the response message is in JSON format and removes Markdown formatting if present.

`pyrit.memory`#

`AzureSQLMemory`	A class to manage conversation memory using Azure SQL Server as the backend database.
`CentralMemory`	Provides a centralized memory instance across the framework.
`DuckDBMemory`	A class to manage conversation memory using DuckDB as the backend database.
`EmbeddingDataEntry`	Represents the embedding data associated with conversation entries in the database.
`MemoryInterface`	Represents a conversation memory that stores chat messages.
`MemoryEmbedding`	The MemoryEmbedding class is responsible for encoding the memory embeddings.
`MemoryExporter`	Handles the export of data to various formats, currently supporting only JSON format.
`PromptMemoryEntry`	Represents the prompt data.

`pyrit.models`#

`ALLOWED_CHAT_MESSAGE_ROLES`	Built-in mutable sequence.
`AudioPathDataTypeSerializer`
`AzureBlobStorageIO`	Implementation of StorageIO for Azure Blob Storage.
`ChatMessage`
`ChatMessagesDataset`	Represents a dataset of chat messages.
`ChatMessageRole`	alias of `Literal`['system', 'user', 'assistant']
`ChatMessageListDictContent`
`construct_response_from_request`	Constructs a response entry from a request.
`DataTypeSerializer`	Abstract base class for data type normalizers.
`data_serializer_factory`
`DiskStorageIO`	Implementation of StorageIO for local disk storage.
`EmbeddingData`
`EmbeddingResponse`
`EmbeddingSupport`
`EmbeddingUsageInformation`
`ErrorDataTypeSerializer`
`group_conversation_request_pieces_by_sequence`	Groups prompt request pieces from the same conversation into PromptRequestResponses.
`Identifier`
`ImagePathDataTypeSerializer`
`PromptRequestPiece`	Represents a prompt request piece.
`PromptResponse`
`PromptResponseError`	alias of `Literal`['blocked', 'none', 'processing', 'unknown']
`PromptDataType`	alias of `Literal`['text', 'image_path', 'audio_path', 'url', 'error']
`PromptRequestResponse`	Represents a response to a prompt request.
`QuestionAnsweringDataset`	Represents a dataset for question answering.
`QuestionAnsweringEntry`	Represents a question model.
`QuestionChoice`	Represents a choice for a question.
`Score`
`ScoreType`	alias of `Literal`['true_false', 'float_scale']
`SeedPrompt`	Represents a seed prompt with various attributes and metadata.
`SeedPromptDataset`	SeedPromptDataset class helps to read a list of seed prompts, which can be loaded from a YAML file.
`SeedPromptGroup`	A group of prompts that need to be sent together.
`StorageIO`	Abstract interface for storage systems (local disk, Azure Storage Account, etc.).
`TextDataTypeSerializer`
`UnvalidatedScore`	Score is an object that validates all the fields.

`pyrit.orchestrator`#

`CrescendoOrchestrator`	The CrescendoOrchestrator class represents an orchestrator that executes the Crescendo attack.
`FlipAttackOrchestrator`	This orchestrator implements the Flip Attack method found here: https://arxiv.org/html/2410.02832v1.
`FuzzerOrchestrator`
`MultiTurnAttackResult`	The result of a multi-turn attack.
`MultiTurnOrchestrator`	The MultiTurnOrchestrator is an interface that coordinates attacks and conversations between a adversarial_chat target and an objective_target.
`Orchestrator`
`PAIROrchestrator`	This orchestrator implements the Prompt Automatic Iterative Refinement (PAIR) algorithm
`PromptSendingOrchestrator`	This orchestrator takes a set of prompts, converts them using the list of PromptConverters, sends them to a target, and scores the resonses with scorers (if provided).
`RedTeamingOrchestrator`	The RedTeamingOrchestrator class orchestrates a multi-turn red teaming attack on a target system.
`ScoringOrchestrator`	This orchestrator scores prompts in a parallelizable and convenient way.
`SkeletonKeyOrchestrator`	Creates an orchestrator that executes a skeleton key jailbreak.
`TreeOfAttacksWithPruningOrchestrator`
`XPIAManualProcessingOrchestrator`
`XPIAOrchestrator`
`XPIATestOrchestrator`

`pyrit.prompt_converter`#

`AddImageTextConverter`	Adds a string to an image and wraps the text into multiple lines if necessary.
`AddTextImageConverter`	Adds a string to an image and wraps the text into multiple lines if necessary.
`AsciiArtConverter`	Converts a string to ASCII art
`AtbashConverter`	Converter to encode prompt using atbash cipher.
`AudioFrequencyConverter`	The AudioFrequencyConverter takes an audio file and shifts its frequency, by default it will shift it above human range (=20kHz).
`AzureSpeechAudioToTextConverter`	The AzureSpeechAudioTextConverter takes a .wav file and transcribes it into text.
`AzureSpeechTextToAudioConverter`	The AzureSpeechTextToAudio takes a prompt and generates a wave file.
`Base64Converter`
`CaesarConverter`	Converter to encode prompt using caesar cipher.
`CharacterSpaceConverter`
`CodeChameleonConverter`	The CodeChameleon Converter uses a combination of personal encryption and decryption functions, code nesting, as well as a set of instructions for the response to bypass LLM safeguards.
`ConverterResult`
`EmojiConverter`
`FlipConverter`
`FuzzerCrossOverConverter`	Fuzzer converter that uses multiple prompt templates to generate new prompts.
`FuzzerExpandConverter`
`FuzzerRephraseConverter`
`FuzzerShortenConverter`
`FuzzerSimilarConverter`
`HumanInTheLoopConverter`	Allows review of each prompt sent to a target before sending it.
`LeetspeakConverter`	Converts a string to a leetspeak version
`LLMGenericTextConverter`
`MaliciousQuestionGeneratorConverter`	A PromptConverter that generates malicious questions using an LLM via an existing PromptTarget (like Azure OpenAI).
`MathPromptConverter`	A PromptConverter that converts natural language instructions into symbolic mathematics problems using an LLM via an existing PromptTarget (like Azure OpenAI or other supported backends).
`MorseConverter`	Converter to encode prompts using morse code.
`NoiseConverter`
`PersuasionConverter`	Converter to rephrase prompts using a variety of persuasion techniques.
`PromptConverter`	A prompt converter is responsible for converting prompts into a different representation.
`QRCodeConverter`	Converts a text string to a QR code image.
`RandomCapitalLettersConverter`	This converter takes a prompt and randomly capitalizes it by a percentage of the total characters.
`RepeatTokenConverter`	Repeat a specified token a specified number of times in addition to a given prompt.
`ROT13Converter`
`SearchReplaceConverter`	Converts a string by replacing chosen phrase with a new phrase of choice
`StringJoinConverter`
`SuffixAppendConverter`
`TenseConverter`
`ToneConverter`
`TranslationConverter`
`UnicodeConfusableConverter`	A PromptConverter that applies substitutions to words in the prompt to test adversarial textual robustness by replacing characters with visually similar ones.
`UnicodeSubstitutionConverter`
`UrlConverter`
`VariationConverter`

`pyrit.prompt_normalizer`#

`PromptNormalizer`
`PromptResponseConverterConfiguration`	Represents the configuration for a prompt response converter.
`NormalizerRequestPiece`
`NormalizerRequest`

`pyrit.prompt_target`#

`AzureBlobStorageTarget`	The AzureBlobStorageTarget takes prompts, saves the prompts to a file, and stores them as a blob in a provided storage account container.
`AzureMLChatTarget`
`CrucibleTarget`
`GandalfLevel`
`GandalfTarget`
`HTTPTarget`	HTTP_Target is for endpoints that do not have an API and instead require HTTP request(s) to send a prompt
`HuggingFaceChatTarget`	The HuggingFaceChatTarget interacts with HuggingFace models, specifically for conducting red teaming activities.
`HuggingFaceEndpointTarget`	The HuggingFaceEndpointTarget interacts with HuggingFace models hosted on cloud endpoints.
`limit_requests_per_minute`	A decorator to enforce rate limit of the target through setting requests per minute.
`OllamaChatTarget`
`OpenAICompletionTarget`
`OpenAIDALLETarget`	The Dalle3Target takes a prompt and generates images This class initializes a DALL-E image target
`OpenAIChatTarget`	This class facilitates multimodal (image and text) input and text output generation
`OpenAITTSTarget`
`OpenAITarget`
`OllamaChatTarget`
`PromptChatTarget`
`PromptShieldTarget`	PromptShield is an endpoint which detects the presence of a jailbreak.
`PromptTarget`
`TextTarget`	The TextTarget takes prompts, adds them to memory and writes them to io which is sys.stdout by default

`pyrit.score`#

`AzureContentFilterScorer`
`ContentClassifierPaths`
`FloatScaleThresholdScorer`	A scorer that applies a threshold to a float scale score to make it a true/false score.
`GandalfScorer`
`HumanInTheLoopScorer`	Create scores from manual human input and adds them to the database.
`LikertScalePaths`
`MarkdownInjectionScorer`
`PromptShieldScorer`	Returns true if an attack or jailbreak has been detected by Prompt Shield.
`Scorer`	Abstract base class for scorers.
`SelfAskCategoryScorer`	A class that represents a self-ask score for text classification and scoring.
`SelfAskLikertScorer`	A class that represents a "self-ask" score for text scoring for a likert scale.
`SelfAskRefusalScorer`	A self-ask scorer detects a refusal.
`SelfAskScaleScorer`	A class that represents a "self-ask" score for text scoring for a customizable numeric scale.
`SelfAskTrueFalseScorer`	A class that represents a self-ask true/false for scoring.
`SubStringScorer`	Scorer that checks if a given substring is present in the text.
`TrueFalseInverterScorer`	A scorer that inverts a true false score.
`TrueFalseQuestion`	A class that represents a true/false question.
`TrueFalseQuestionPaths`