This briefing outlines how each step of the SAFE AI Framework has been designed to support trustworthy AI.
Authors: McElhinney, Mazumder, Tjalve, Madigan, Spencer
Based on the National Institute of Standards and Technology (NIST) AI Risk Management Framework, the seven characteristics of trustworthy AI are:
Valid and Reliable: The AI system should perform as intended, delivering accurate results consistently across different situations.
Safe: The system must not produce harmful or dangerous outcomes to human life, health, property, or the environment.
Secure and Resilient: The AI must withstand unforeseen events, attacks, or adversarial inputs, maintaining its functionality without compromising data.
Accountable and Transparent: There should be a clear understanding of how the system operates, including documentation on data, decisions, and responsibility for its outputs.
Explainable and Interpretable: Users should understand the reasoning behind a particular output or decision made by the AI.
Privacy-Enhanced: The system must protect sensitive data, uphold privacy standards, and avoid leaking information across sessions.
Fair with Harmful Bias Managed: The AI must treat different user groups equitably, actively identifying and mitigating bias in training data or results.