Skip to content

Latest commit

 

History

History
79 lines (52 loc) · 3.09 KB

CONTRIBUTING.md

File metadata and controls

79 lines (52 loc) · 3.09 KB
Raw

Contributing to OllaDeck

First off, thank you for considering contributing to OllaDeck! It's people like you that make OllaDeck such a great tool for the AI security community.

Why Contribute?

OllaDeck is in dire need of contributions, especially in the areas of:

  1. Red team tools for text-based generative AI
  2. Blue team tools for text-based generative AI
  3. Relevant datasets for testing and improving AI security

Your contributions will help build a comprehensive repository that the AI security community can use to improve the robustness and security of generative AI systems.

How Can I Contribute?

Reporting Bugs

  • Ensure the bug was not already reported by searching on GitHub under Issues.
  • If you're unable to find an open issue addressing the problem, open a new one. Be sure to include a title and clear description, as much relevant information as possible, and a code sample or an executable test case demonstrating the expected behavior that is not occurring.

Suggesting Enhancements

  • Open a new issue with your suggestion.
  • Clearly describe the enhancement and the motivation for it.
  • Provide examples of how the enhancement would be used.

Code Contributions

  1. Fork the repository.
  2. Create a new branch (git checkout -b feature/AmazingFeature).
  3. Make your changes.
  4. Commit your changes (git commit -m 'Add some AmazingFeature').
  5. Push to the branch (git push origin feature/AmazingFeature).
  6. Open a Pull Request.

Tool Contributions

We are actively seeking contributions in the following areas:

Red Team Tools

  • Tools for crafting adversarial prompts
  • Frameworks for testing AI model robustness
  • Utilities for exploring potential data leakage or privacy concerns

Blue Team Tools

  • Monitoring systems for AI model outputs
  • Implementations of safeguards against prompt injection and other AI-specific attacks
  • Tools for ensuring compliance with ethical AI guidelines
  • Analyzers for AI-generated content to detect potential security risks

Dataset Contributions

We welcome contributions of datasets that can be used for:

  • Training more robust AI models
  • Testing AI systems against various attack vectors
  • Benchmarking the performance of security measures

When contributing datasets, please ensure:

  • You have the right to share the data
  • The data is anonymized if it contains sensitive information
  • You provide clear documentation on the dataset's contents and structure

Style Guidelines

  • Follow PEP 8 style guide for Python code.
  • Write clear, commented code.
  • Provide comprehensive documentation for new features or tools.

Code of Conduct

Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.

Questions?

If you have any questions, please feel free to contact the project maintainers or open an issue for discussion.

Thank you for your interest in improving OllaDeck! Your contributions will help make AI systems more secure and robust.