PyRIT
PyRIT copied to clipboard
Azure
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...
We recently discovered https://safetyprompts.com/, which has so many datasets! We need help going through the website and creating a list of relevant datasets. A relevant dataset is one which contains...
> Name: TrustAIRLab/forbidden_question_set > > Link: https://github.com/verazuo/jailbreak_llms/blob/main/data/forbidden_question/forbidden_question_set.csv > > Relevant Columns: "content_policy_name","question" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394548943)_ --- ### Describe the solution you'd like This dataset should be available...
> Name: LibrAI/do-not-answer > > Link: https://huggingface.co/datasets/LibrAI/do-not-answer > > Relevant Columns: "risk_area","types_of_harm","specific_harms","question" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394581998)_ --- ### Describe the solution you'd like This dataset should be available...
> Name: McGill-NLP/stereoset > > Link: https://huggingface.co/datasets/McGill-NLP/stereoset > > Relevant columns: "target", "bias_type", "context", "sentences" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394702074)_ --- ### Describe the solution you'd like This dataset...
> Name: hendrycks/ethics > > Link: https://huggingface.co/datasets/hendrycks/ethics > > Relevant columns: "label","input" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394733669)_ --- ### Describe the solution you'd like This dataset should be available...
> Name: SALT-NLP/mic > > Link: https://www.dropbox.com/sh/m46z42nce8x0ttk/AABuSZiA6ESyrJNWmgTPrfuRa?dl=0 > > Relevant columns: "Q","A","rot","moral","rot-agree","A_agrees","violation-severity","worker_answer" > > > > Note: rot is rule of thumb _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394732149)_ --- ###...
> Name: Anthropic/model-written-evals > > Link: https://huggingface.co/datasets/Anthropic/model-written-evals > > Relevant columns: "question", "answer_matching_behavior" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394713228)_ --- ### Describe the solution you'd like This dataset should be...
> Name: Babelscape/ALERT > > Link: https://huggingface.co/datasets/Babelscape/ALERT > > Relevant columns: "category", "prompt" _Originally posted by @divyaamin9825 in [#429](https://github.com/Azure/PyRIT/issues/429#issuecomment-2394716529)_ --- ### Describe the solution you'd like This dataset should be...
### Overview This PR introduces the **Malicious Question Generator** converter, adapted from Project Moonshot. The converter uses an LLM (through the `PromptTarget`) to generate cybersecurity-related malicious questions in Python list...
#### Describe the issue linked to the documentation The following links show occurrences of the (since removed in #375 ) powershell scripts in our docs. https://github.com/search?q=repo%3AAzure%2FPyRIT+pct_to_ipynb&type=code https://github.com/search?q=repo%3AAzure%2FPyRIT+ipynb_to_pct&type=code #### Suggest a...
