The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.
Investigate the best way to integrate, e.g., as an orchestrator, and propose a high-level plan here. Then, maintainers will provide feedback and help with questions during the implementation phase.
Describe alternatives you've considered, if relevant
Is your feature request related to a problem? Please describe.
The technique from this repo is not captured in PyRIT yet https://github.com/tml-epfl/llm-adaptive-attacks
Describe the solution you'd like
Investigate the best way to integrate, e.g., as an orchestrator, and propose a high-level plan here. Then, maintainers will provide feedback and help with questions during the implementation phase.
Describe alternatives you've considered, if relevant
-
Additional context
-