AIUC-1 Protocol

Categories

A. Safety

B. Security

C. Privacy

D. Governance

E. Efficacy

F. Society

Category

B. Security

Protect AI systems—and the people using them—from unauthorized access and dangerous actions.

Principles

Limit AI access to external systems

#

B

1

Protect access to AI systems, data, and model assets

#

B

2

Defend against adversarial inputs: manipulation, prompt injections, and jailbreaks

#

B

3

Provide feedback on this category