Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

BUG harm categories for AdvBench Dataset aren't added yet #730

Open
eugeniavkim opened this issue Feb 21, 2025 · 1 comment · May be fixed by #732
Open

BUG harm categories for AdvBench Dataset aren't added yet #730

eugeniavkim opened this issue Feb 21, 2025 · 1 comment · May be fixed by #732
Assignees
@paulinek13
Labels
datasets Pulling in external datasets into PyRIT good first issue Good for newcomers help wanted Extra attention is needed

Comments

@eugeniavkim
Copy link
Contributor

eugeniavkim commented Feb 21, 2025 •
edited
Loading

The fetch_adv_bench_dataset currently does not have any applied harm categories to the different prompts. We want to be able to use this dataset with harm category filters and this requires we manually apply category labels to the dataset to use in PyRIT.

This may look like adding harm categories in a separate file to import into PyRIT instead of using this CSV file in the fetch function here: https://github.com/Azure/PyRIT/blob/main/pyrit/datasets/fetch_example_datasets.py
@eugeniavkim eugeniavkim added datasets Pulling in external datasets into PyRIT good first issue Good for newcomers labels Feb 21, 2025
@romanlutz romanlutz added the help wanted Extra attention is needed label Feb 22, 2025
@romanlutz romanlutz changed the title Manually add harm categories to AdvBench Dataset BUG harm categories for AdvBench Dataset aren't added yet Feb 22, 2025
@paulinek13
Copy link
Contributor

Hi! I'd like to work on this issue 😃

To make sure I understand the task correctly, I'll open a draft PR with a proposed approach so that you can check it and confirm if it looks good before I move forward with full categorization and filtering support. Thanks!

@paulinek13 paulinek13 linked a pull request Feb 22, 2025 that will close this issue
Draft
@eugeniavkim eugeniavkim mentioned this issue Feb 25, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@paulinek13 paulinek13

Labels
datasets Pulling in external datasets into PyRIT good first issue Good for newcomers help wanted Extra attention is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

[DRAFT] add harm categories to AdvBench Dataset paulinek13/PyRIT
3 participants
@romanlutz @eugeniavkim @paulinek13