AI engineering glossary · Evals guardrails AI security
What is model inversion?
Model inversion: An attack that uses a model's outputs to reconstruct sensitive information about its training data, such as approximating a face from a face-recognition model. It shows that releasing a model or its confidence scores can leak private attributes.
Model inversion: an example
By repeatedly querying a face classifier for one person, an attacker gradually recovers a blurry image resembling that person.
Related terms
More Evals guardrails AI security terms
- Model signing
- Model supply chain attack
- Multimodal prompt injection
- NeMo Guardrails
- NIST AI Risk Management Framework
- Offline evaluation
- Online evaluation
- Output guardrail
Where you learn it
Model inversion is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.