FEAT: Adversarial Models Blog Post - #2519
Open
Victor Valbuena (ValbuenaVC) wants to merge 24 commits into
Open
Conversation
Victor Valbuena (ValbuenaVC)
changed the title
Richard Lundeen (rlundeen2)
approved these changes
Sep 1, 2026
Richard Lundeen (rlundeen2)
left a comment
Richard Lundeen (rlundeen2)
left a comment
Contributor
There was a problem hiding this comment.
Looks good! Approved with smallish things
Victor Valbuena (ValbuenaVC)
changed the title
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
Victor Valbuena (ValbuenaVC)
changed the title
Victor Valbuena (ValbuenaVC)
marked this pull request as ready for review
September 1, 2026 23:20
Sarah Cooley (scooley)
left a comment
Sarah Cooley (scooley)
left a comment
There was a problem hiding this comment.
Added non-blocking recomendations
|
|
||
| *Figure 4 - Paired head-to-head across 14 objectives per technique-model pair. Hatched bars required recovery; the strict clean aggregate excludes those techniques.* | ||
|
|
||
| The sanitized technique-level records behind the preliminary studies are available in [CSV form](2026_09_03_adversarial_model_selection_results.csv). |
Contributor
There was a problem hiding this comment.
what are the blank cells ?
Contributor
Author
There was a problem hiding this comment.
They're supposed to contain failure and error subcounts for the study, but I don't think we kept that information, so I'm going to set that to not_reported for consistency
|
|
||
| ## Limitations and Next Steps | ||
|
|
||
| The adversarial benchmark is available for you to try as the `AdversarialBenchmark` class. See [Benchmark Scenarios](../scanner/benchmark.ipynb) for its behavior, configuration, and examples. |
Contributor
There was a problem hiding this comment.
do we usually link to the ipynb file in the github repo vs on the website ?
Contributor
Author
There was a problem hiding this comment.
I found three references to notebooks in the last scoring blog post (2026_04_14_scoring_scorers.md), so we have done it, but if you feel it's not relevant I can remove it
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Blog post for the adversarial model benchmark (
AdversarialBenchmark) in PyRIT. The blog post explains what adversarial models are, why they matter in PyRIT, and what happened when we created and ran a benchmarking scenario on them. Small datasets and graphs are attached in this PR.Tests and Documentation
N/A. All changes are under
/doc/blog.