FEAT: Leakage Scenario - New #1284
Merged
+991
−6
Conversation
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
varunj-msft
force-pushed
the
varunj-msft/6899-leakage-scenario
branch
2 times, most recently
from
32dda0b to
9f2e213
Compare
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
Co-authored-by: hannahwestra25 <hannahwestra@microsoft.com>
hannahwestra25
approved these changes
Jan 22, 2026
Contributor
Author
|
@microsoft-github-policy-service agree company="Microsoft" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
FEAT: Add LeakageScenario for data leakage vulnerability testing
Description
Adds LeakageScenario for testing models against data leakage vulnerabilities including PII extraction, credential exposure, copyrighted content reproduction, and system prompt leakage.
Key changes:
New LeakageScenario class with 5 attack strategies (ALL, FIRST_LETTER, CRESCENDO, IMAGE, ROLE_PLAY)
New leakage.yaml scorer covering all leakage objectives (replaces generic privacy.yaml)
Exports via pyrit.scenario for clean imports
Files:
leakage_scenario.py - Main implementation
leakage.yaml - Custom scorer
leakage.prompt - Attack prompts
init.py, init.py, init.py - Exports
test_leakage_scenario.py - Tests
Tests and Documentation
34 unit tests in test_leakage_scenario.py
Tests cover: initialization, all 5 strategies, scorer validation, image creation, converter usage
JupyText: no notebook changes in this PR