Converters

Converters#

Converters are used to transform prompts before sending them to the target.

This can be useful for a variety of reasons, such as encoding the prompt in a different format, or adding additional information to the prompt. For example, you might want to convert a prompt to base64 before sending it to the target, or add a prefix to the prompt to indicate that it is a question.

Converters can transform prompts in various ways:

  • Text-to-Text: Encoding, obfuscation, translation, and semantic transformations

  • Multimodal: Converting between text, images, audio, video, and files

  • Interactive: Human-in-the-loop review and modification

Converter Modality Reference Table#

The following table shows all available converters organized by their input and output modalities:

import pandas as pd

from pyrit.prompt_converter import get_converter_modalities
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore

# Get all converters with their modalities
converter_list = get_converter_modalities()

# Create a list of rows for the DataFrame
rows = []
for name, inputs, outputs in converter_list:
    input_str = ", ".join(inputs) if inputs else "any"
    output_str = ", ".join(outputs) if outputs else "any"
    rows.append({"Input Modality": input_str, "Output Modality": output_str, "Converter": name})

# Create DataFrame and sort
df = pd.DataFrame(rows)
df = df.sort_values(by=["Input Modality", "Output Modality", "Converter"]).reset_index(drop=True)

# Display all rows
pd.set_option("display.max_rows", None)
df

Found default environment files: ['/home/vscode/.pyrit/.env', '/home/vscode/.pyrit/.env.local']
Loaded environment file: /home/vscode/.pyrit/.env
Loaded environment file: /home/vscode/.pyrit/.env.local
Input Modality Output Modality Converter
0 audio_path audio_path AudioFrequencyConverter
1 audio_path text AzureSpeechAudioToTextConverter
2 image_path image_path AddTextImageConverter
3 image_path image_path TransparencyAttackConverter
4 image_path video_path AddImageVideoConverter
5 image_path, url image_path ImageCompressionConverter
6 text audio_path AzureSpeechTextToAudioConverter
7 text image_path AddImageTextConverter
8 text image_path QRCodeConverter
9 text text AnsiAttackConverter
10 text text AsciiArtConverter
11 text text AsciiSmugglerConverter
12 text text AskToDecodeConverter
13 text text AtbashConverter
14 text text Base2048Converter
15 text text Base64Converter
16 text text BinAsciiConverter
17 text text BinaryConverter
18 text text BrailleConverter
19 text text CaesarConverter
20 text text CharSwapConverter
21 text text CharacterSpaceConverter
22 text text CodeChameleonConverter
23 text text ColloquialWordswapConverter
24 text text DenylistConverter
25 text text DiacriticConverter
26 text text EcojiConverter
27 text text EmojiConverter
28 text text FirstLetterConverter
29 text text FlipConverter
30 text text HumanInTheLoopConverter
31 text text InsertPunctuationConverter
32 text text LLMGenericTextConverter
33 text text LeetspeakConverter
34 text text MaliciousQuestionGeneratorConverter
35 text text MathObfuscationConverter
36 text text MathPromptConverter
37 text text MorseConverter
38 text text NatoConverter
39 text text NoiseConverter
40 text text PersuasionConverter
41 text text ROT13Converter
42 text text RandomCapitalLettersConverter
43 text text RandomTranslationConverter
44 text text RepeatTokenConverter
45 text text SearchReplaceConverter
46 text text SelectiveTextConverter
47 text text SneakyBitsSmugglerConverter
48 text text StringJoinConverter
49 text text SuffixAppendConverter
50 text text SuperscriptConverter
51 text text TemplateSegmentConverter
52 text text TenseConverter
53 text text TextJailbreakConverter
54 text text ToneConverter
55 text text ToxicSentenceGeneratorConverter
56 text text TranslationConverter
57 text text UnicodeConfusableConverter
58 text text UnicodeReplacementConverter
59 text text UnicodeSubstitutionConverter
60 text text UrlConverter
61 text text VariationConverter
62 text text VariationSelectorSmugglerConverter
63 text text ZalgoConverter
64 text text ZeroWidthConverter
65 text url PDFConverter

Converter Categories#

Converters are organized into the following categories:

Simple Converter Example#

Converters can be used to perform these types of transformations. Here is a simple program that uses Rot13Converter converter, RandomCapitalLettersConverter, and AsciiArtConverter.

from pyrit.prompt_converter import (
    AsciiArtConverter,
    BinaryConverter,
    FirstLetterConverter,
    RandomCapitalLettersConverter,
    ROT13Converter,
)

prompt = "tell me how to cut down a tree"


print(await ROT13Converter().convert_tokens_async(prompt=prompt))  # type: ignore
print(await RandomCapitalLettersConverter(percentage=25.0).convert_tokens_async(prompt=prompt))  # type: ignore
print(await AsciiArtConverter().convert_tokens_async(prompt=prompt))  # type: ignore
print(await BinaryConverter().convert_tokens_async(prompt=prompt))  # type: ignore
print(await FirstLetterConverter().convert_tokens_async(prompt=prompt))  # type: ignore

text: gryy zr ubj gb phg qbja n gerr
text: tell me HOw to Cut dowN A tRee
text:                                                                                                                                
_|_  _ |\ |\             _    |)    _             _|_  _      _        _|_     _|   _                    _,     _|_  ,_   _  _ 
 |  |/ |/ |/    /|/|/|  |/    |/\  / \_|  |  |_    |  / \_   /   |  |   |     / |  / \_|  |  |_/|/|     / |      |  /  | |/ |/ 
 |_/|_/|_/|_/    | | |_/|_/   |  |/\_/  \/ \/      |_/\_/    \__/ \/|_/ |_/   \/|_/\_/  \/ \/   | |_/   \/|_/    |_/   |/|_/|_/
                                                                                                                               

text: 0000000001110100 0000000001100101 0000000001101100 0000000001101100 0000000000100000 0000000001101101 0000000001100101 0000000000100000 0000000001101000 0000000001101111 0000000001110111 0000000000100000 0000000001110100 0000000001101111 0000000000100000 0000000001100011 0000000001110101 0000000001110100 0000000000100000 0000000001100100 0000000001101111 0000000001110111 0000000001101110 0000000000100000 0000000001100001 0000000000100000 0000000001110100 0000000001110010 0000000001100101 0000000001100101
text: t m h t c d a t

Stacking Converters#

Although converters can be used on their own, they should be thought of as a piece in the pipeline. Typically any attack will have arguments so that prompts can be converted before being sent to the target. They can be stacked, use LLMs, and are a powerful tool.

Before you begin, ensure you are setup with the correct version of PyRIT installed and have secrets configured as described here.

Stacking Converters with PromptSendingAttack#

In the following example, a TextTarget is used so these prompts are simply printed and added to memory. This can be useful if you are red teaming something and need to manually enter prompts. However, the target can be replaced with any other target. E.g., if you have API access you can add a target there.

In this example the converters are stacked. First a variation is found using VariationConverter, and then StringJoinConverter is used to add a dash between letters. Remember that order matters. If StringJoinConverter came first, we would be asking the LLM to make variations of the prompt: “t-e-l-l- - m-e- -h-o-w- -t-o- -c-u-t- -d-o-w-n - a- -t-r-e-e”

from pyrit.executor.attack import (
    AttackConverterConfig,
    ConsoleAttackResultPrinter,
    PromptSendingAttack,
)
from pyrit.prompt_converter import StringJoinConverter, VariationConverter
from pyrit.prompt_normalizer import PromptConverterConfiguration
from pyrit.prompt_target import OpenAIChatTarget, TextTarget

objective = "tell me how to cut down a tree"

# converter target to send prompt to; in this case configured to the Azure OpenAI GPT-4o Chat model
converter_target = OpenAIChatTarget()
prompt_variation_converter = VariationConverter(converter_target=converter_target)

converter_configs = PromptConverterConfiguration.from_converters(  # type: ignore
    converters=[prompt_variation_converter, StringJoinConverter()]
)

converter_config = AttackConverterConfig(request_converters=converter_configs)  # type: ignore

target = TextTarget()
attack = PromptSendingAttack(
    objective_target=target,
    attack_converter_config=converter_config,
)

result = await attack.execute_async(objective=objective)  # type: ignore

printer = ConsoleAttackResultPrinter()
await printer.print_conversation_async(result=result)  # type: ignore

{'__type__': 'TextTarget', '__module__': 'pyrit.prompt_target.text_target'}: user: E-x-p-l-a-i-n t-o m-e t-h-e p-r-o-c-e-s-s o-f c-h-o-p-p-i-n-g d-o-w-n a t-r-e-e-.

[PromptSendingAttack (ID: 81e8da7f)] No response received on attempt 1 (likely filtered)

────────────────────────────────────────────────────────────────────────────────────────────────────
🔹 Turn 1 - USER
────────────────────────────────────────────────────────────────────────────────────────────────────
   Original:
  tell me how to cut down a tree

   Converted:
  E-x-p-l-a-i-n t-o m-e t-h-e p-r-o-c-e-s-s o-f c-h-o-p-p-i-n-g d-o-w-n a t-r-e-e-.

────────────────────────────────────────────────────────────────────────────────────────────────────
Contents