.. LLM-PBE documentation master file.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

Welcome to LLM-PBE's documentation!
===================================

**LLM-PBE** is a toolkit to assess the data privacy of LLMs. It has the following features

- Comprehensive attack approaches (data extraction attacks, membership inference attacks, jailbreaking attacks, prompt injection attacks).
- Practical defense approaches (differential privacy, machine unlearning, defensive prompting).
- Multiple types of data (personally-identificable information, copywrited work, domain knowledge, prompts).
- Accessing different LLMs (GPT-3.5/4, HuggingFace, TogetherAI, etc).

.. image:: ./images/components.png
   :align: center
   :target: ./images/components.png

.. toctree::
   :maxdepth: 1
   :caption: Contents:

      Quick Start <Quick-Start>
      APIs/Parameters <Parameters>
      Examples <Examples>
      Experiments <Experiments>