Definition
Model extraction involves querying a target machine learning model’s API to infer its internal structure, weights, or decision boundaries. Attackers use these queries to build a surrogate model that mimics the original, potentially stealing intellectual property or bypassing security measures. This threat highlights the vulnerability of proprietary models exposed via public interfaces without sufficient rate limiting or monitoring.
Summary
An attack where an adversary queries a model to reconstruct its parameters or create a surrogate copy.
Key Concepts
- Surrogate Modeling
- API Querying
- Intellectual Property Theft
- Adversarial Attack
Use Cases
- Security auditing of commercial AI APIs
- Protecting proprietary algorithms from cloning
- Researching defense mechanisms against extraction