I.0452Indicator
Probes AI models to extract training data
Crafts probing queries to reconstruct sensitive data from AI training sets.
Classification
- Risk domain One of 9 areas of human risk, from social engineering to readiness and response. Every signal belongs to one.
- Category
- Evidence level
- Maturity practices One capability a program performs, scored on its own: See, Understand, Act, Prove, Govern and Culture.
- Mappings
-
Indicators carry no mappings of their own; the signals in the same risk domain do.
Related signals (same domain, dimension and polarity)
4Cite this term
"Probes AI models to extract training data" (I.0452), Human Risk Management Framework v2.0.0, Living Security, CC BY 4.0. https://www.humanriskmanagement.com/taxonomy/indicators/i-0452-probes-ai-models-to-extract-training-data
Part of the open HRM Taxonomy, CC BY 4.0. Download the taxonomy as JSON · What's new in 2.0.
The initial assessment
Find your level.Then fix what matters.
18 questions, about 4 minutes and nothing to type before the result: your level, a score for each practice and three first playbooks, each Easy, Medium or Hard.