FEAT: add benchmark-owned adversarial prompts - #2494
Open
hannahwestra25 wants to merge 12 commits into
Open
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 545c2d8d-1fe9-451d-a8bc-da23e19b3737
Replace the user-supplied prompt override with scenario-local prompt variants for the benchmark's role-play, simulated Crescendo, and TAP techniques. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 545c2d8d-1fe9-451d-a8bc-da23e19b3737
hannahwestra25
force-pushed
the
hannahwestra25-scenario-adversarial-system-prompt
branch
from
August 25, 2026 21:09
62452c8 to
84be7c0
Compare
hannahwestra25
changed the title
Adapt the supplied single-turn and multi-turn prompts to the adversarial_chat schema and prepend them to the corresponding benchmark technique prompts. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 545c2d8d-1fe9-451d-a8bc-da23e19b3737
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 545c2d8d-1fe9-451d-a8bc-da23e19b3737
hannahwestra25
changed the title
This reverts commit d4b29b5.
hannahwestra25
changed the title
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 545c2d8d-1fe9-451d-a8bc-da23e19b3737
This reverts commit 0f96620.
hannahwestra25
changed the title
hannahwestra25
changed the title
hannahwestra25
changed the title
hannahwestra25
marked this pull request as ready for review
August 26, 2026 16:39
hannahwestra25
commented
Aug 26, 2026
| @@ -0,0 +1,84 @@ | |||
| name: adversarial_benchmark_crescendo_simulated | |||
| description: | | |||
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
1 participant
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.
What changed
AdversarialBenchmarknow uses benchmark-specific system prompts for its three default techniques:role_play_video_game,crescendo_simulated, andtap.The prompts are applied through scenario-local factories, so the globally registered techniques stay unchanged. There’s no new scanner setting or generic prompt API. The scenario version is bumped to 5 because this changes default benchmark behavior.
aligned the Leakage and benchmark factory helpers on
_extra_default_factories().Testing
210 targeted benchmark, Leakage, factory, schema, and scenario tests pass. Ruff checks pass too.