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

FEAT Prompt Shield #271

Merged
merged 30 commits into from
Aug 14, 2024
Merged

FEAT Prompt Shield #271

merged 30 commits into from
Aug 14, 2024

Conversation

ValbuenaVC
Copy link
Contributor

@ValbuenaVC ValbuenaVC commented Jul 2, 2024 •
edited
Loading

Description

Added:

  • PromptShieldTarget: Jailbreak/attack detector using the Prompt Shield Content Safety Resource.
  • PromptShieldScorer: A true/false scorer returning True when an attack is detected.
  • Change to net_utility in pyrit/common to accept HTTPS params as an argument in make_request_and_raise_if_error().

Tests

  • PromptShieldTarget: Completed
  • PromptShieldScorer: Completed

TODO

  • Jupytext file code
  • Fix api version hardcoding
  • Finish tests
  • Add keys to keyvault

@ValbuenaVC
Copy link
Contributor Author

@microsoft-github-policy-service agree company="Microsoft"

@blakebullwinkel
Copy link
Contributor

Great work @ValbuenaVC ! I think you can remove the "DRAFT" tag from the title as this PR is actively being reviewed.

ValbuenaVC added 2 commits July 9, 2024 18:09
@ValbuenaVC
Merge branch 't-vivalbuena/PromptShield' of https://github.com/Valbue…
caa639e 
…naVC/PyRIT into t-vivalbuena/PromptShield

Adding jupytext-generated .py files for the Prompt Shield tutorials.
@ValbuenaVC
Added more unit tests
cfb646b
@rlundeen2 rlundeen2 merged commit affbaf7 into Azure:main Aug 14, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@rdheekonda rdheekonda rdheekonda left review comments

@nina-msft nina-msft nina-msft left review comments

@romanlutz romanlutz romanlutz approved these changes

@rlundeen2 rlundeen2 rlundeen2 approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
6 participants
@ValbuenaVC @blakebullwinkel @romanlutz @rdheekonda @rlundeen2 @nina-msft