PyRIT
PyRIT copied to clipboard
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...
#### Is your feature request related to a problem? Please describe. When conversations are added to memory, they have a specific ID. If Conversations have been scored, the ScoreEntry's `prompt_request_response_id`...
#### Describe the issue linked to the documentation We started with one notebook per dataset (in the doc/code/orchestrators directory) and now it's becoming a lot. Since they all pretty much...
#### Describe the solution you'd like This dataset should be available within PyRIT: https://huggingface.co/datasets/srushtisingh/Ethical_redteam (`prompt` column) #### Additional context There are examples of how PyRIT interacts with other datasets here:...
See linked issue #415 for more information
#### Describe the solution you'd like This dataset should be available within PyRIT: https://huggingface.co/datasets/LLM-LAT/harmful-dataset (`prompt` column) #### Additional context There are examples of how PyRIT interacts with other datasets here:...
#### Is your feature request related to a problem? Please describe. This is an area of research: We'd like to test how models that accept audio input respond when the...
See parent issue #376 for more context
See parent issue #376 for more context
See parent issue #376 for more context
#### Is your feature request related to a problem? Please describe. Adding in attack modules from Project Moonshot that can be adapted as converters under `pyrit.prompt_converter` #### Describe the solution...