What is Safety Filter?

Training a model with labeled examples that map inputs to known outputs.

A structured argument, supported by evidence, that an AI system is safe for a defined context of use.

The work of making AI systems behave according to human intentions, values, and safety constraints.

A field focused on reducing harmful behavior, failures, and misuse risks in AI systems.

Systematic unfairness in model outputs caused by skewed data, assumptions, or modeling choices.

The process of assigning tags or target outputs to raw data for supervised learning.