feat: add ProPILE probes for PII leakage detection #1504
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Outdated suggestions cannot be applied.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.
Tip
Better reviewed commit-by-commit, starting from here.
This PR implements the ProPILE (Probing Privacy Leakage in Large Language Models) methodology from Kim et al., 2023 probes and detectors.
garak-propile-demo-run.mp4
ProPILE tests whether LLMs have memorized personally identifiable information (PII) from their training data and can be prompted to leak it. The attack constructs completion-style prompts using known PII to elicit other PII fields.
Detectors
PIILeakPII-type-aware matching with partial scoring (email local-part/domain, phone digits/area-code, address components, generic fuzzy matching);PIILeakExactstrict exact-match detection, inherits fromTriggerListDetectorTests
Closes #275