Security, privacy, and fairness · MLD-0261
Data extraction
Recovering sensitive, memorized, or otherwise restricted information from a model or system.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Test whether a model reveals training records.
Original caveat
Exact extraction and attribute inference are different threat types.
Context and aliases
Level: Intermediate. Stages: Data · Training · Evaluation · Deployment · Governance.
Tags: ML · DL · SLM · LLM · Security · Privacy · Safety.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- The Algorithmic Foundations of Differential Privacy ↗ · Reference link
- Google Machine Learning Glossary ↗ · Consulted
- OWASP Top 10 for LLM Applications ↗ · Reference link
- Original reference URL ↗