Skip to main content

FAQs

H2O Model Security is an application that enables data scientists to evaluate and analyze the security of Driverless AI (DAI) models (experiments). With different model attacks, H2O Model Security centralizes and visualizes how DAI models will react to different intentional and unintentional model attacks in production.

The below sections provide answers to frequently asked questions. If you have additional questions, please send them to cloud-feedback@h2o.ai.

General​

Which specific model attacks are available to evaluate and analyze the security of a Driverless AI model?​

Available model attacks are as follows:

What is the general flow of a model attack in H2O Model Security?​

To learn about the general flow of a model attack in H2O Model Security, see Model security flow.

Feedback