Skip to main content

The Python Risk Identification Tool for LLMs (PyRIT) is a library used to assess the robustness of LLMs

Project description

Python Risk Identification Tool for generative AI (PyRIT)

The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and ML engineers to red team foundation models and their applications.

Introduction

PyRIT is a library developed by the AI Red Team for researchers and engineers to help them assess the robustness of their LLM endpoints against different harm categories such as fabrication/ungrounded content (e.g., hallucination), misuse (e.g., bias), and prohibited content (e.g., harassment).

PyRIT automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft).​

The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Additionally, this tool allows researchers to iterate and improve their mitigations against different harms. For example, at Microsoft we are using this tool to iterate on different versions of a product (and its metaprompt) so that we can more effectively protect against prompt injection attacks.

PyRIT architecture

Where can I learn more?

Microsoft Learn has a dedicated page on AI Red Teaming.

Check out our docs for more information on how to install PyRIT, our How to Guide, and more, as well as our demos folder.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyrit-0.3.0.tar.gz (205.0 kB view details)

Uploaded Source

Built Distribution

pyrit-0.3.0-py3-none-any.whl (327.9 kB view details)

Uploaded Python 3

File details

Details for the file pyrit-0.3.0.tar.gz.

File metadata

  • Download URL: pyrit-0.3.0.tar.gz
  • Upload date:
  • Size: 205.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for pyrit-0.3.0.tar.gz
Algorithm Hash digest
SHA256 edbe4d9acd59d59c18233ff711a4e299f566bdf4b355eabd3d2d422559ab3638
MD5 e780d2d4f2e9b665f299d4a1106e20f8
BLAKE2b-256 18b051cec552e5755f2ac5ad43fef98c8bb0a2a24733c777245d38bb6a53cab2

See more details on using hashes here.

File details

Details for the file pyrit-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: pyrit-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 327.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.9

File hashes

Hashes for pyrit-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d76319d72dd970cc1295cec5c283d3b75c7dc4543cd55a69a5b66f6408f31cd3
MD5 2634703771ba2410cdc46b522ab44aa0
BLAKE2b-256 fb578a76eda1b4763c84f38f19e009360745263e03e72baaafee793d28c8851d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page