Research

Our research investigates how generative AI systems can be governed, measured, and secured — so that powerful tools stay useful without becoming unverifiable.

Categories

01

Security

The Security team maps public standards and voluntary frameworks to practice for generative and agentic AI systems.

02

Safety

Life, health, property, and environment.

03

Validity

Does the system do what it claims, with documented limits.

04

Accountability

Who is responsible, and can others inspect what happened.

05

Explainability

Can people understand outputs and behavior.

06

Privacy

Anonymity, confidentiality, and control of data.

07

Fairness

Harmful bias and discrimination risk.

Papers